© 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. 54049
    Prev
    Next
    INDEX
    Explanations

    references to downloading and ensuring product safety

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    iki
    -0.07
    ut
    -0.06
    an
    -0.06
    elt
    -0.06
    ion
    -0.06
     Franken
    -0.06
     considering
    -0.06
     McInt
    -0.05
    arch
    -0.05
     bat
    -0.05
    POSITIVE LOGITS
    cribe
    0.08
    upertino
    0.07
    à¹Ħà¸Ķ
    0.07
    ampo
    0.07
    ον
    0.07
    exus
    0.07
    ç¿°
    0.07
    å¼ĺ
    0.06
    cce
    0.06
    ãĤ¸ãĤ¢
    0.06
    Activations Density 0.011%

    No Known Activations