© 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. 57728
    Prev
    Next
    INDEX
    Explanations

    elements related to authorship and publication details

    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
    /ay
    -0.06
    æīį
    -0.06
    _COMPAT
    -0.06
    èĵ
    -0.06
    783
    -0.06
    uevo
    -0.06
    istrator
    -0.06
    /bind
    -0.06
    гл
    -0.06
    Overview
    -0.06
    POSITIVE LOGITS
    malink
    0.08
     siden
    0.07
     addCriterion
    0.07
    ../../../../
    0.07
    elden
    0.06
    ukarı
    0.06
    nech
    0.06
    ZeroWidthSpace
    0.06
     related
    0.06
    dfs
    0.06
    Activations Density 0.044%

    No Known Activations