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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 79555
    Prev
    Next
    INDEX
    Explanations

    dialogue and conversational exchanges about filmmaking and personal experiences

    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
    eyh
    -0.07
    emey
    -0.07
    mada
    -0.07
    antu
    -0.07
    ancock
    -0.07
    inç
    -0.07
    untime
    -0.07
    važ
    -0.07
    ekler
    -0.07
    argin
    -0.07
    POSITIVE LOGITS
     answer
    0.10
     interview
    0.09
     interviewer
    0.09
    answer
    0.08
    answered
    0.08
    åĽŀçŃĶ
    0.08
     Interview
    0.08
     Answer
    0.08
     answers
    0.07
    erview
    0.07
    Activations Density 0.075%

    No Known Activations