© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80127
    Prev
    Next
    INDEX
    Explanations

    mentions of lists or rankings related to individuals or groups

    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
    uyo
    -0.08
    uchos
    -0.07
    Reviewer
    -0.07
    istrovstvÃŃ
    -0.07
    oltip
    -0.07
    nist
    -0.07
    ยà¸Ļ
    -0.07
    .examples
    -0.07
    /cop
    -0.06
    oux
    -0.06
    POSITIVE LOGITS
     poss
    0.09
     possibilities
    0.09
     possibility
    0.08
     mentioned
    0.07
     odds
    0.07
     handic
    0.07
     Altern
    0.07
     Poss
    0.07
     potential
    0.06
    åı¯èĥ½æĢ§
    0.06
    Activations Density 0.009%

    No Known Activations