© 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. 104120
    Prev
    Next
    INDEX
    Explanations

    expressions of interest in biographical roles and film projects

    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
    /tos
    -0.08
    ICAST
    -0.07
    NECT
    -0.07
    hani
    -0.07
    _weak
    -0.07
    Âłmiles
    -0.07
    gaard
    -0.07
     hafta
    -0.07
     Charges
    -0.07
    setParameter
    -0.07
    POSITIVE LOGITS
     next
    0.09
    next
    0.07
     future
    0.07
     decentral
    0.06
     nxt
    0.06
     apprec
    0.06
    emoc
    0.06
    0.06
    chk
    0.06
     spur
    0.06
    Activations Density 0.023%

    No Known Activations