© 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. 126035
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly of individuals and possibly their affiliations or titles

    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
    PG
    -0.07
    ovice
    -0.07
    ounce
    -0.06
    ainment
    -0.06
    uento
    -0.06
    gang
    -0.06
    olah
    -0.06
    olumn
    -0.06
    ÂĢ
    -0.06
    itere
    -0.06
    POSITIVE LOGITS
     fitte
    0.06
     기ìŀIJ
    0.06
    yses
    0.06
     huy
    0.06
    tae
    0.06
    polator
    0.06
     Zack
    0.05
    Åijs
    0.05
     Wade
    0.05
    _principal
    0.05
    Activations Density 0.032%

    No Known Activations