© 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. 92595
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agency and fraudulent actions

    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
    è²´
    -0.09
    otte
    -0.08
    acÃŃ
    -0.08
    untu
    -0.08
    rosso
    -0.07
    onis
    -0.07
    adele
    -0.07
    à¸Ĭาà¸ķ
    -0.07
     poil
    -0.07
    ÅĦst
    -0.07
    POSITIVE LOGITS
     fid
    0.06
    ule
    0.06
     tr
    0.06
     duty
    0.06
     acting
    0.06
     Victorian
    0.06
    oram
    0.06
     c
    0.06
     Q
    0.06
     Duty
    0.06
    Activations Density 0.006%

    No Known Activations