© 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. 5-LLAMASCOPE-RES-131K
    6. 126042
    Prev
    Next
    INDEX
    Explanations

    function calls related to the creation of objects or models

    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
    inium
    -0.06
     Shutdown
    -0.06
    -p
    -0.06
    ache
    -0.06
    atura
    -0.06
    ue
    -0.05
    linger
    -0.05
     nhẹ
    -0.05
    away
    -0.05
    bara
    -0.05
    POSITIVE LOGITS
    yonel
    0.07
    äm
    0.07
    igne
    0.07
    AtPath
    0.07
    istream
    0.07
    aload
    0.07
     Truy
    0.07
    ê²ł
    0.07
    ymoon
    0.06
    itaire
    0.06
    Activations Density 0.026%

    No Known Activations