© 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. 17-LLAMASCOPE-RES-131K
    11. 3245
    Prev
    Next
    INDEX
    Explanations

    phrases related to the generation or emergence of entities or events

    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
     maybe
    -0.09
     certainly
    -0.08
     really
    -0.07
     might
    -0.07
     just
    -0.06
     perhaps
    -0.06
    ,
    -0.06
     you
    -0.06
     right
    -0.06
     like
    -0.06
    POSITIVE LOGITS
    uthor
    0.08
    entionPolicy
    0.07
    iggins
    0.07
    fuck
    0.07
    currently
    0.07
    .createQuery
    0.07
    ugo
    0.07
    isContained
    0.07
     âĸĪâĸĪ
    0.07
    _mv
    0.07
    Activations Density 0.000%

    No Known Activations