© 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. 28-LLAMASCOPE-RES-32K
    11. 17300
    Prev
    Next
    INDEX
    Explanations

    references to states and state-related discussions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    arus
    -0.19
    asser
    -0.17
     states
    -0.17
    _states
    -0.17
    InstanceState
    -0.16
     States
    -0.16
    States
    -0.16
    çĬ¶æĢģ
    -0.15
    arians
    -0.15
    ãĤ£
    -0.15
    POSITIVE LOGITS
    wide
    0.39
    -wide
    0.30
    Wide
    0.28
     wide
    0.28
    house
    0.27
    /local
    0.27
    hood
    0.25
     Wide
    0.24
     tro
    0.23
    houses
    0.19
    Activations Density 0.034%

    No Known Activations