© 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. 87696
    Prev
    Next
    INDEX
    Explanations

    names and references to individuals, particularly in a historical or cultural context

    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
    edor
    -0.07
     bew
    -0.06
    ãģ¼
    -0.06
    ulses
    -0.06
     Hop
    -0.06
     dw
    -0.06
     enjo
    -0.06
    ãĤŃãĥ¥
    -0.06
     Bew
    -0.06
    784
    -0.06
    POSITIVE LOGITS
    ERIC
    0.09
    lernen
    0.07
    eric
    0.07
     Subset
    0.07
    zburg
    0.07
    bart
    0.07
    arma
    0.06
    ront
    0.06
    ld
    0.06
    peri
    0.06
    Activations Density 0.028%

    No Known Activations