© 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. 17-LLAMASCOPE-RES-131K
    11. 31550
    Prev
    Next
    INDEX
    Explanations

    references to albums and their creators

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    รà¸ģ
    -0.08
    ãĤ¹ãĥ¬
    -0.08
    (æ°´
    -0.07
    ÑĶм
    -0.07
    ÑĢиз
    -0.07
    ForResult
    -0.07
    Interop
    -0.07
    ẩu
    -0.07
    iry
    -0.07
    mani
    -0.07
    POSITIVE LOGITS
    hold
    0.07
    var
    0.06
     Cup
    0.06
    /by
    0.06
    /to
    0.06
    too
    0.06
    ue
    0.05
    :
    0.05
    asi
    0.05
    ngth
    0.05
    Activations Density 0.003%

    No Known Activations