© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 105964
    Prev
    Next
    INDEX
    Explanations

    references to categories or classifications

    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
    ams
    -0.07
     Swe
    -0.06
    hor
    -0.06
    insky
    -0.06
    agues
    -0.06
    elo
    -0.06
    ½æķ°
    -0.06
    ACA
    -0.05
     Hull
    -0.05
    ingles
    -0.05
    POSITIVE LOGITS
    ког
    0.07
    é¤
    0.07
    -ÐIJ
    0.07
    ISIBLE
    0.07
    prak
    0.07
    매
    0.06
     sao
    0.06
    ục
    0.06
    .MixedReality
    0.06
    gart
    0.06
    Activations Density 0.000%

    No Known Activations