© 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. 103998
    Prev
    Next
    INDEX
    Explanations

    references to media, public relations, and support services

    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
    lio
    -0.07
    igon
    -0.07
    ora
    -0.07
    ensis
    -0.07
    ulling
    -0.07
    .openg
    -0.07
    idon
    -0.06
    oran
    -0.06
    idding
    -0.06
    nowledge
    -0.06
    POSITIVE LOGITS
    ums
    0.07
    nech
    0.07
    gba
    0.06
    onest
    0.06
     Maxim
    0.06
     Obl
    0.06
    ê¶ģ
    0.06
    837
    0.06
    ctal
    0.06
     zas
    0.06
    Activations Density 0.021%

    No Known Activations