© 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. 93628
    Prev
    Next
    INDEX
    Explanations

    references to licenses or copyright information

    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
    -0.07
     (
    -0.07
    erot
    -0.07
    upy
    -0.06
    er
    -0.06
     someone
    -0.05
     in
    -0.05
    vis
    -0.05
    ourt
    -0.05
    509
    -0.05
    POSITIVE LOGITS
    ÑĢиг
    0.08
    elden
    0.08
     Dön
    0.07
    \Resources
    0.07
    /licenses
    0.07
    .sep
    0.07
    -SA
    0.07
    à¤¿à¤Ľ
    0.07
    /drivers
    0.07
    rios
    0.07
    Activations Density 0.002%

    No Known Activations