© 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. 61156
    Prev
    Next
    INDEX
    Explanations

    SQL clauses related to data retrieval

    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
    ardy
    -0.08
    οÏĤ
    -0.07
    .Automation
    -0.07
     ↵↵
    -0.07
    buie
    -0.07
    اÙ
    -0.07
    feito
    -0.07
     Ù¾Úĺ
    -0.07
    TokenType
    -0.07
    agements
    -0.07
    POSITIVE LOGITS
     contin
    0.07
     squ
    0.06
    363
    0.06
    odelist
    0.06
    qrt
    0.06
    osal
    0.06
    oty
    0.06
    adel
    0.05
     Brow
    0.05
    tbl
    0.05
    Activations Density 0.002%

    No Known Activations