© 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. 125074
    Prev
    Next
    INDEX
    Explanations

    question marks and related punctuation indicating inquiries

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

    Questions in a Q&A format that are followed by responses, with the question ending with delimiters and the response beginning with delimiters.

    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
    ient
    -0.06
    転
    -0.06
    essa
    -0.06
     portion
    -0.06
    vn
    -0.06
    iously
    -0.06
     Happy
    -0.06
    esso
    -0.06
     Ú©ÙĨار
    -0.06
    portion
    -0.06
    POSITIVE LOGITS
    Cancelable
    0.08
    ANS
    0.08
    reply
    0.08
     Replies
    0.08
     Answer
    0.07
    .setTo
    0.07
    ernals
    0.07
    _Collections
    0.07
     Ans
    0.07
    -reply
    0.07
    Activations Density 0.017%

    No Known Activations