Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29354
    Prev
    Next
    INDEX
    Explanations

    conversational elements and punctuation that indicate dialogue

    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
    važ
    -0.06
    èm
    -0.06
    Ä
    -0.06
     depart
    -0.06
     Tamb
    -0.06
    ême
    -0.06
     completeness
    -0.06
    Ã
    -0.06
    .MixedReality
    -0.06
    awns
    -0.06
    POSITIVE LOGITS
     egt
    0.07
    ehler
    0.07
    RESS
    0.06
    UpInside
    0.06
    leftright
    0.06
    .simps
    0.06
    ARAM
    0.06
    OTE
    0.06
    oes
    0.06
    endet
    0.06
    Activations Density 0.008%

    No Known Activations