Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4975
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or proper names, particularly "Port."

    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
    ptune
    -0.07
    brero
    -0.07
    anja
    -0.07
    erken
    -0.07
    usto
    -0.06
    icação
    -0.06
    поÑĢ
    -0.06
    idle
    -0.06
    ingle
    -0.06
    oten
    -0.06
    POSITIVE LOGITS
    .Framework
    0.07
    eus
    0.07
    ominator
    0.06
    ela
    0.06
    eous
    0.06
     sans
    0.06
    '&&
    0.06
     Roland
    0.06
    LAT
    0.06
    illo
    0.06
    Activations Density 0.003%

    No Known Activations