© 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. 73687
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to financial and legal contexts

    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
    istrovstvÃŃ
    -0.10
     pstmt
    -0.08
    dere
    -0.07
    ãĥ³ãĤ¿
    -0.07
    iyon
    -0.07
    /cms
    -0.07
    markt
    -0.07
    èĨ
    -0.07
    .mvc
    -0.07
     maduras
    -0.07
    POSITIVE LOGITS
     Madness
    0.13
    achuset
    0.08
    (M
    0.07
     Mondays
    0.07
     Minute
    0.06
    ificent
    0.06
    olog
    0.06
     m
    0.06
    =M
    0.06
     Magic
    0.06
    Activations Density 1.719%

    No Known Activations