© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61932
    Prev
    Next
    INDEX
    Explanations

    references to configurable settings or options

    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
    options
    -0.08
     options
    -0.07
    option
    -0.07
    ugg
    -0.07
    ipsis
    -0.06
    oppel
    -0.06
     option
    -0.06
    oulos
    -0.06
    iente
    -0.06
    _Options
    -0.06
    POSITIVE LOGITS
    ahoma
    0.08
    inç
    0.07
     reass
    0.06
    vido
    0.06
     Beit
    0.06
    gger
    0.06
     Kostenlose
    0.06
    osite
    0.06
    osit
    0.06
    LEGRO
    0.06
    Activations Density 0.012%

    No Known Activations