© 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. 90404
    Prev
    Next
    INDEX
    Explanations

    references to online services or transactions

    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
    lease
    -0.08
    itesse
    -0.06
    /release
    -0.06
    aina
    -0.06
    isser
    -0.06
    igos
    -0.06
    hani
    -0.06
    横
    -0.06
    onis
    -0.06
     دس
    -0.06
    POSITIVE LOGITS
    rick
    0.07
    ngen
    0.06
    appen
    0.06
    SDK
    0.06
    adro
    0.06
     Murphy
    0.06
    ENDOR
    0.06
    /ion
    0.06
    GLuint
    0.06
    /internal
    0.06
    Activations Density 0.005%

    No Known Activations