© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119767
    Prev
    Next
    INDEX
    Explanations

    conversational questioning and dialogue elements

    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
    loh
    -0.07
    ilar
    -0.07
    Reviewer
    -0.07
    illet
    -0.07
    ÑĤоÑĦ
    -0.07
     Conversation
    -0.06
    aller
    -0.06
     prospect
    -0.06
     Jer
    -0.06
    lp
    -0.06
    POSITIVE LOGITS
     guesses
    0.11
     guessed
    0.10
     answer
    0.09
    çŃĶæ¡Ī
    0.09
     answers
    0.09
     guess
    0.08
     correct
    0.08
    uess
    0.08
    answer
    0.08
     Answers
    0.07
    Activations Density 0.010%

    No Known Activations