© 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. 5782
    Prev
    Next
    INDEX
    Explanations

    programming-related functions and properties

    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
    uellement
    -0.07
    æĪ¸
    -0.06
    dob
    -0.06
    xes
    -0.05
    icamente
    -0.05
    yn
    -0.05
     Homo
    -0.05
    owel
    -0.05
    ĭ
    -0.05
    ово
    -0.05
    POSITIVE LOGITS
    aviest
    0.09
    SWG
    0.08
    .nativeElement
    0.08
    liest
    0.07
    iest
    0.07
    ëĭĿ
    0.07
    ObjectContext
    0.07
    skirts
    0.07
    aurant
    0.07
    rarian
    0.07
    Activations Density 0.072%

    No Known Activations