© 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. 81211
    Prev
    Next
    INDEX
    Explanations

    verbs relating to guidance or consequences

    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
     Verd
    -0.07
    ÑĭÑģ
    -0.06
    reau
    -0.06
    uel
    -0.06
    Subview
    -0.06
    inte
    -0.06
     Lak
    -0.06
    Superview
    -0.06
    tha
    -0.06
    sein
    -0.05
    POSITIVE LOGITS
     us
    0.07
    wand
    0.07
    eger
    0.07
    ehr
    0.07
    ıma
    0.07
    enders
    0.06
    lasting
    0.06
    ÑĪибка
    0.06
    vá
    0.06
    tern
    0.06
    Activations Density 0.009%

    No Known Activations