© 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. 76132
    Prev
    Next
    INDEX
    Explanations

    references to scientific journals and publications

    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
    @student
    -0.07
    ¢
    -0.06
     Brady
    -0.06
    464
    -0.06
     Gro
    -0.06
    olds
    -0.06
    /functions
    -0.06
    \Modules
    -0.06
     Opport
    -0.06
    289
    -0.06
    POSITIVE LOGITS
    ATAL
    0.07
    ATAB
    0.07
    ese
    0.06
    æµ·å¤ĸ
    0.06
    OTTOM
    0.06
    ató
    0.06
     ActiveForm
    0.06
    ä»Ģ
    0.06
    xlim
    0.06
    ugins
    0.06
    Activations Density 0.011%

    No Known Activations