© 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. 69165
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    achi
    -0.07
     rival
    -0.07
    anic
    -0.06
    onga
    -0.06
    /theme
    -0.06
     Gree
    -0.06
     prze
    -0.05
    tere
    -0.05
    -0.05
    he
    -0.05
    POSITIVE LOGITS
    piar
    0.08
    çon
    0.07
    ĶåĽŀ
    0.07
     Undefined
    0.07
    ̣
    0.07
    ÄĽr
    0.07
    UrlParser
    0.07
     Whilst
    0.07
    bjerg
    0.07
    /WebAPI
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.