© 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. 15-LLAMASCOPE-RES-131K
    11. 103640
    Prev
    Next
    INDEX
    Explanations

    JavaScript function definitions and properties

    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
    inson
    -0.06
    ози
    -0.06
    ainter
    -0.06
     dirent
    -0.06
    quate
    -0.06
    ODE
    -0.06
    steder
    -0.06
     ought
    -0.06
     unsub
    -0.06
     pParent
    -0.06
    POSITIVE LOGITS
    zig
    0.07
    .BLL
    0.06
    atin
    0.06
     Kun
    0.06
     Goth
    0.06
     Hayden
    0.06
     Hugo
    0.06
     craw
    0.06
     Placeholder
    0.06
    inan
    0.06
    Activations Density 0.001%

    No Known Activations