© 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. 105048
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ibri
    -0.07
    SingleOrDefault
    -0.07
    _ulong
    -0.06
    ////////////////////////////////////////////////////
    -0.06
    .times
    -0.06
    @a
    -0.06
    bz
    -0.06
    PageSize
    -0.06
    ιÏĥμ
    -0.06
    agas
    -0.06
    POSITIVE LOGITS
    ormsg
    0.06
    çİī
    0.06
     Hib
    0.06
     RT
    0.06
    egen
    0.06
    uzzer
    0.05
    -tabs
    0.05
     Nicol
    0.05
    ês
    0.05
    ordo
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.