© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 24147
    Prev
    Next
    INDEX
    Explanations

    occurrences of conditional phrases or scenarios relating to cases or situations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    the phrase "in (some/the/one/both/etc.) case(s)" or similar constructions that introduce specific examples or instances.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    roe
    -0.16
    tsy
    -0.16
    лим
    -0.14
    ãĥŃãĥ¼
    -0.14
    vp
    -0.14
    stan
    -0.13
    RAP
    -0.13
    alus
    -0.13
    ablo
    -0.13
    ayment
    -0.13
    POSITIVE LOGITS
     case
    0.34
     caso
    0.29
    case
    0.28
     cases
    0.27
    _case
    0.24
     Case
    0.24
    -case
    0.23
    .case
    0.23
    cases
    0.23
    åł´åIJĪãģ¯
    0.23
    Activations Density 0.094%

    No Known Activations