© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78794
    Prev
    Next
    INDEX
    Explanations

    sections or elements that are empty or lack content

    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
    .gf
    -0.08
    uÄį
    -0.08
    енÑĮ
    -0.08
    utow
    -0.08
    eil
    -0.08
    ÙĩÙĨ
    -0.07
     ngh
    -0.07
    ãģĸ
    -0.07
    gün
    -0.07
    gom
    -0.07
    POSITIVE LOGITS
     (
    0.07
     of
    0.07
     cit
    0.06
    uri
    0.06
     decent
    0.06
     Bath
    0.06
     a
    0.06
     numbers
    0.06
     
    0.06
     absolute
    0.06
    Activations Density 0.000%

    No Known Activations