© 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. 87114
    Prev
    Next
    INDEX
    Explanations

    questions that indicate inquiry or requests for information

    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
    nob
    -0.07
    het
    -0.07
    éı¡
    -0.07
    _advance
    -0.07
    avic
    -0.06
    Gem
    -0.06
    hait
    -0.06
    ấc
    -0.06
    Ãły
    -0.06
     Gat
    -0.06
    POSITIVE LOGITS
    ans
    0.08
     answer
    0.08
    ANS
    0.08
    answer
    0.07
     answers
    0.07
    -answer
    0.07
     answered
    0.07
    enum
    0.06
     reply
    0.06
     replies
    0.06
    Activations Density 0.010%

    No Known Activations