© 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. 126520
    Prev
    Next
    INDEX
    Explanations

    patterns related to specific types of words or phrases that contain particular characters or symbols

    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
     آذ
    -0.07
    ushman
    -0.07
    egie
    -0.07
    azzi
    -0.07
    Ñīий
    -0.07
    eed
    -0.07
    elez
    -0.07
    uthor
    -0.06
    ruba
    -0.06
    rchive
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.07
    .bunifuFlatButton
    0.06
    ads
    0.06
    lime
    0.06
    Ħ
    0.06
     Gordon
    0.06
    ndl
    0.06
    ãĥ¼ãĥĨãĤ£
    0.06
    uluk
    0.06
    ata
    0.06
    Activations Density 0.002%

    No Known Activations