© 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. 91842
    Prev
    Next
    INDEX
    Explanations

    conditional expressions and logical operators in code

    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
     ep
    -0.06
     zen
    -0.06
     emerg
    -0.06
    float
    -0.06
    ilia
    -0.06
     trú
    -0.06
    lix
    -0.05
    om
    -0.05
    nil
    -0.05
     smo
    -0.05
    POSITIVE LOGITS
    OAD
    0.07
    اط
    0.07
    RowAt
    0.07
    onga
    0.07
     NSStringFromClass
    0.07
    inski
    0.07
    _oid
    0.07
    rahim
    0.07
    ç´
    0.07
    raç
    0.07
    Activations Density 0.001%

    No Known Activations