© 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 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. 85863
    Prev
    Next
    INDEX
    Explanations

    question and answer structures or dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    A colon that appears immediately after "A" or "Answer" in a question-and-answer format, indicating the start of a response or solution to a previously stated question.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ucky
    -0.07
    otate
    -0.07
    incinn
    -0.06
     -$
    -0.06
     sed
    -0.06
    ñas
    -0.06
    vat
    -0.06
    ñana
    -0.06
    eldon
    -0.06
     Logical
    -0.06
    POSITIVE LOGITS
     amen
    0.07
    .Mode
    0.06
    219
    0.06
    299
    0.06
    brates
    0.06
    ossal
    0.06
    287
    0.06
     knack
    0.06
    211
    0.06
    205
    0.06
    Activations Density 0.006%

    No Known Activations