© 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. 15-LLAMASCOPE-RES-131K
    11. 90165
    Prev
    Next
    INDEX
    Explanations

    mentions of people and their actions or characteristics

    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
    ardy
    -0.07
     Preston
    -0.07
    illes
    -0.06
     being
    -0.06
    ucus
    -0.06
    yal
    -0.06
    ilent
    -0.06
    pedia
    -0.06
    ye
    -0.06
    riend
    -0.06
    POSITIVE LOGITS
    cooked
    0.06
    ewood
    0.06
    gm
    0.06
    apl
    0.06
     nons
    0.06
    campo
    0.06
    /rem
    0.06
    idar
    0.06
    ipation
    0.06
    anos
    0.06
    Activations Density 0.063%

    No Known Activations