© 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. 104048
    Prev
    Next
    INDEX
    Explanations

    references to specific items or elements being discussed or described

    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
    vá
    -0.06
    rix
    -0.06
    lod
    -0.06
    elog
    -0.06
     pri
    -0.06
    ainter
    -0.06
    hasOne
    -0.06
    ot
    -0.06
    alim
    -0.06
    ÑĨен
    -0.06
    POSITIVE LOGITS
    curity
    0.10
    rens
    0.09
    omba
    0.08
     who
    0.08
    cales
    0.07
    achuset
    0.07
    -ci
    0.07
     same
    0.07
     CreateMap
    0.07
    ông
    0.07
    Activations Density 0.029%

    No Known Activations