© 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. 61752
    Prev
    Next
    INDEX
    Explanations

    instances of questions and inquiries made during discussions or interviews

    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
    leta
    -0.07
    ÅĤaw
    -0.07
    ettel
    -0.07
    arse
    -0.07
    abcdefghijklmnop
    -0.07
    utan
    -0.07
    erville
    -0.07
     γλη
    -0.07
    Å©
    -0.07
    phia
    -0.07
    POSITIVE LOGITS
     question
    0.08
     asked
    0.07
     ques
    0.06
     questions
    0.06
     zda
    0.06
     concerned
    0.06
     pregunta
    0.06
     prompted
    0.06
    ida
    0.06
     concern
    0.06
    Activations Density 0.016%

    No Known Activations