© 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. 42241
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly question marks

    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
    ibri
    -0.09
     имÑĥ
    -0.08
    #__
    -0.08
    ajes
    -0.08
    heimer
    -0.08
    isFunction
    -0.08
    ostel
    -0.08
    /*č↵
    -0.08
    [js
    -0.07
    loub
    -0.07
    POSITIVE LOGITS
    ¸
    0.07
    Answer
    0.07
    0.07
    arn
    0.06
     answer
    0.06
    ote
    0.06
    ena
    0.05
     answered
    0.05
     reply
    0.05
    unt
    0.05
    Activations Density 0.002%

    No Known Activations