© 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. 22-LLAMASCOPE-RES-131K
    11. 4105
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or physical addresses

    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
    oop
    -0.06
     butterfly
    -0.06
    yro
    -0.06
    phants
    -0.06
    egas
    -0.06
    uddle
    -0.06
    .gray
    -0.06
    uo
    -0.06
    884
    -0.06
    unker
    -0.06
    POSITIVE LOGITS
     boarding
    0.08
    _HOOK
    0.07
    boys
    0.07
    girls
    0.07
     crossorigin
    0.07
    TZ
    0.07
     boys
    0.07
     programu
    0.07
    POSIT
    0.07
     girls
    0.06
    Activations Density 0.000%

    No Known Activations