© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5718
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their variations

    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
    ,
    -0.07
    oor
    -0.06
     format
    -0.06
    าà¸ļ
    -0.06
    .
    -0.06
    овоÑĢ
    -0.06
    fk
    -0.05
    onth
    -0.05
     upon
    -0.05
     picnic
    -0.05
    POSITIVE LOGITS
    kus
    0.08
    LOCKS
    0.08
    erie
    0.08
    Streamer
    0.08
    asher
    0.07
    .scalablytyped
    0.07
    .allocate
    0.07
    #ac
    0.07
    ï½¥
    0.07
    presso
    0.07
    Activations Density 0.003%

    No Known Activations