© 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. 126354
    Prev
    Next
    INDEX
    Explanations

    names of universities and colleges

    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
    æłªå¼ıä¼ļ社
    -0.08
    å±±å¸Ĥ
    -0.07
    echa
    -0.06
     Lieutenant
    -0.06
    ghan
    -0.06
    VD
    -0.06
     ash
    -0.06
    bai
    -0.06
     Eag
    -0.06
     branch
    -0.06
    POSITIVE LOGITS
    iple
    0.06
    áct
    0.06
     pand
    0.06
     Koh
    0.06
    .logical
    0.06
    TECTED
    0.06
    atak
    0.06
     Mines
    0.06
    Ł³
    0.06
    еÑĢк
    0.06
    Activations Density 0.096%

    No Known Activations