© 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. 5-LLAMASCOPE-RES-131K
    11. 126615
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions in research or scientific 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
    sez
    -0.07
    hausen
    -0.07
    .Unicode
    -0.07
    egra
    -0.07
    airo
    -0.07
    istine
    -0.07
     addCriterion
    -0.06
     ÎĶε
    -0.06
     charge
    -0.06
    zet
    -0.06
    POSITIVE LOGITS
    ê³Ħ
    0.07
    lep
    0.07
    coni
    0.06
     TRACE
    0.06
     Logs
    0.06
    511
    0.06
     Besch
    0.06
    ưỡng
    0.06
    uš
    0.06
    acr
    0.06
    Activations Density 0.015%

    No Known Activations