© 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. 71056
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS elements or structure

    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
    shaw
    -0.08
     outr
    -0.07
    ÏĨι
    -0.07
    semb
    -0.07
    ibus
    -0.06
    Äįe
    -0.06
    DED
    -0.06
     ford
    -0.06
    rahim
    -0.06
    annel
    -0.06
    POSITIVE LOGITS
    506
    0.06
    kaar
    0.06
    :nth
    0.06
    ª
    0.06
     Mash
    0.06
     LoginComponent
    0.05
    дин
    0.05
    indle
    0.05
     Schro
    0.05
    637
    0.05
    Activations Density 0.000%

    No Known Activations