© 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. 31367
    Prev
    Next
    INDEX
    Explanations

    words associated with finality or completion in various 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
    athon
    -0.08
    avan
    -0.07
    stu
    -0.07
    azzo
    -0.06
    eree
    -0.06
    unsch
    -0.06
    etable
    -0.06
    apyrus
    -0.06
    ï¸
    -0.06
    ledged
    -0.06
    POSITIVE LOGITS
    ow
    0.09
    orses
    0.07
    OW
    0.07
    owment
    0.07
     result
    0.07
    519
    0.06
    871
    0.06
    PEnd
    0.06
    aight
    0.06
     careers
    0.06
    Activations Density 0.013%

    No Known Activations