© 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. 28232
    Prev
    Next
    INDEX
    Explanations

    URL and string-related formatting patterns

    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
     âĵĺ
    -0.08
     ë³´ë©´
    -0.07
    .vars
    -0.07
    vio
    -0.07
    å¢
    -0.07
    achs
    -0.07
     liá»ĩu
    -0.06
    bins
    -0.06
     Tay
    -0.06
    Yii
    -0.06
    POSITIVE LOGITS
    etc
    0.06
     etc
    0.06
     downright
    0.06
    éré
    0.06
    akin
    0.06
     suf
    0.06
    رÙĤ
    0.05
     Causes
    0.05
    _exact
    0.05
     equivalent
    0.05
    Activations Density 0.020%

    No Known Activations