© 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. 84522
    Prev
    Next
    INDEX
    Explanations

    key identifiers or labels in a structured format, specifically the presence of important terms or titles

    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
    ulen
    -0.06
    aven
    -0.06
    mlink
    -0.06
    ateur
    -0.05
    entrant
    -0.05
    ewise
    -0.05
    plen
    -0.05
    ered
    -0.05
    aken
    -0.05
     literature
    -0.05
    POSITIVE LOGITS
    .xhtml
    0.09
     zku
    0.07
     suyu
    0.07
    zione
    0.07
    سط
    0.07
    áž
    0.07
    Cro
    0.07
    _fm
    0.07
    PRETTY
    0.07
    _FM
    0.07
    Activations Density 0.009%

    No Known Activations