© 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. 9-LLAMASCOPE-RES-131K
    11. 95561
    Prev
    Next
    INDEX
    Explanations

    references to religious texts and their chapters

    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
    allee
    -0.06
    rå
    -0.06
    iefs
    -0.06
    ÎŃλ
    -0.06
     Leban
    -0.06
     Dante
    -0.06
    elu
    -0.06
    ANTE
    -0.06
    HING
    -0.06
    éī
    -0.06
    POSITIVE LOGITS
    AttributeValue
    0.06
    /runtime
    0.06
    ums
    0.06
    ewn
    0.06
     ::::::::
    0.06
    typed
    0.06
     YaÅŁ
    0.06
    orial
    0.06
    ĶåĽŀ
    0.06
    .nextSibling
    0.06
    Activations Density 0.000%

    No Known Activations