© 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 EvalsExportsAPI 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. 60941
    Prev
    Next
    INDEX
    Explanations

    terms related to predictions and future outcomes

    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
    ÅĽcie
    -0.07
    elda
    -0.07
    oro
    -0.07
    É
    -0.07
    fen
    -0.06
    lub
    -0.06
    alus
    -0.06
    pei
    -0.06
    agi
    -0.06
    極
    -0.06
    POSITIVE LOGITS
     sơ
    0.07
    .dd
    0.06
    abr
    0.06
     prob
    0.06
     expectation
    0.06
     expectations
    0.06
    itt
    0.06
    trainer
    0.06
     Чи
    0.06
    ErrorCode
    0.06
    Activations Density 0.001%

    No Known Activations