© 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. 63286
    Prev
    Next
    INDEX
    Explanations

    references to font styles or attributes in programming contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    enerate
    -0.07
    isque
    -0.06
    yclic
    -0.06
    quence
    -0.06
    lical
    -0.06
    licit
    -0.06
    peria
    -0.06
    eteor
    -0.06
    rov
    -0.06
    ikut
    -0.06
    POSITIVE LOGITS
    екаÑĢ
    0.08
     domin
    0.07
    roids
    0.07
    HOOK
    0.07
     cryptographic
    0.06
    _SR
    0.06
    ılı
    0.06
    ONES
    0.06
    галÑĸ
    0.06
    utzer
    0.06
    Activations Density 0.000%

    No Known Activations