© 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. 76974
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals who are preceded in death or by relationships and heritage

    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
    ãĤ¹ãĥ¬
    -0.07
    ADOR
    -0.07
    éģº
    -0.07
    estate
    -0.07
    ovánÃŃ
    -0.07
    orda
    -0.07
    ENDOR
    -0.07
    éģĹ
    -0.07
    kili
    -0.07
    notated
    -0.07
    POSITIVE LOGITS
     parents
    0.06
    ierge
    0.06
     Dirt
    0.06
    agus
    0.06
    /of
    0.06
    ãĥ¼ãĥĭ
    0.06
    ünde
    0.05
    aside
    0.05
    parents
    0.05
    veis
    0.05
    Activations Density 0.001%

    No Known Activations