© 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. 90337
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and pronouns used in conversational context

    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
    Reviewed
    -0.06
    YPE
    -0.06
     Darling
    -0.06
     Tarif
    -0.06
    ly
    -0.06
    VERR
    -0.06
    _RUNTIME
    -0.06
    VED
    -0.06
    otten
    -0.06
    лÑĭ
    -0.06
    POSITIVE LOGITS
    oman
    0.06
     Cler
    0.06
    ãĤ¤ãĤ¯
    0.06
     Colbert
    0.06
    ewis
    0.06
    wing
    0.06
    ego
    0.06
     accommod
    0.06
    ÑĢеб
    0.06
    úp
    0.06
    Activations Density 0.035%

    No Known Activations