© 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. 82740
    Prev
    Next
    INDEX
    Explanations

    references to individuals and organizations

    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
     hang
    -0.06
    839
    -0.06
     Branch
    -0.06
    iv
    -0.06
     branching
    -0.06
    zw
    -0.06
     Contr
    -0.06
     identity
    -0.06
    oute
    -0.05
    оÑĩкÑĥ
    -0.05
    POSITIVE LOGITS
    allen
    0.07
    arResult
    0.07
    quat
    0.07
    laden
    0.07
    ynos
    0.07
     Woods
    0.07
    ridged
    0.07
    raid
    0.07
    icens
    0.07
    .datatables
    0.07
    Activations Density 0.003%

    No Known Activations