© 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. 2-LLAMASCOPE-RES-32K
    11. 9208
    Prev
    Next
    INDEX
    Explanations

    the word "that" used in various contexts, indicating a focus on clauses or beliefs

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    avel
    -0.17
    istry
    -0.16
    аÑİ
    -0.16
    Ñģим
    -0.15
    sert
    -0.15
    icana
    -0.14
    Lint
    -0.14
    дÑĢом
    -0.14
    ocab
    -0.14
    raci
    -0.14
    POSITIVE LOGITS
     aspir
    0.17
     Brooks
    0.15
    InProgress
    0.15
    chter
    0.15
     absolute
    0.14
     Archie
    0.14
     inout
    0.14
     Hos
    0.14
     Pepper
    0.14
    lac
    0.14
    Activations Density 0.060%

    No Known Activations