© 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. 92548
    Prev
    Next
    INDEX
    Explanations

    evaluative language regarding artistic or creative works

    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
    OS
    -0.07
     Afro
    -0.06
    WS
    -0.06
     gam
    -0.06
     Double
    -0.06
     OS
    -0.06
    iselect
    -0.06
    Double
    -0.06
     conversation
    -0.06
     Fol
    -0.06
    POSITIVE LOGITS
    ogne
    0.08
    -REAL
    0.07
    interp
    0.07
    /effects
    0.07
     copyrighted
    0.07
    ,eg
    0.07
    opher
    0.07
    _Msk
    0.07
    oten
    0.07
    åĥ
    0.07
    Activations Density 0.000%

    No Known Activations