© 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. 82578
    Prev
    Next
    INDEX
    Explanations

    programming code structures and logic

    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
    anka
    -0.10
    $MESS
    -0.07
    TextWriter
    -0.07
    važ
    -0.06
    út
    -0.06
    pdata
    -0.06
    инкÑĥ
    -0.06
    ousel
    -0.06
    getVar
    -0.06
    orney
    -0.06
    POSITIVE LOGITS
    APTER
    0.07
    ivan
    0.06
    otal
    0.06
    igest
    0.06
    illard
    0.06
    uent
    0.06
    "crypto
    0.06
     Westbrook
    0.06
     pick
    0.06
    semblies
    0.06
    Activations Density 0.020%

    No Known Activations