© 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. 16261
    Prev
    Next
    INDEX
    Explanations

    dialogue and conversational elements in the text

    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
    ÏĦί
    -0.08
    illance
    -0.07
    eid
    -0.07
    entiful
    -0.07
    .ul
    -0.07
     VÅ¡ech
    -0.07
     nothing
    -0.07
    ulan
    -0.07
    ARSE
    -0.07
    byn
    -0.07
    POSITIVE LOGITS
     nor
    0.12
     Nor
    0.12
     some
    0.12
    some
    0.11
    nor
    0.10
     sometimes
    0.10
     Some
    0.10
    Some
    0.09
    Nor
    0.09
     Sometimes
    0.09
    Activations Density 0.059%

    No Known Activations