© 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. 28889
    Prev
    Next
    INDEX
    Explanations

    variables related to user account information

    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
    bra
    -0.06
    fas
    -0.06
    ão
    -0.06
    oga
    -0.06
    aliz
    -0.06
    393
    -0.05
    827
    -0.05
    823
    -0.05
    vore
    -0.05
    ee
    -0.05
    POSITIVE LOGITS
     cocci
    0.07
    ascus
    0.07
    ÏĨο
    0.07
    оба
    0.07
    æŃ
    0.07
    otel
    0.06
    anners
    0.06
     addCriterion
    0.06
    rich
    0.06
    ensing
    0.06
    Activations Density 0.000%

    No Known Activations