© 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. 30469
    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
     PÅĻed
    -0.06
    ATAL
    -0.06
     cos
    -0.06
     Brill
    -0.06
    Obsolete
    -0.06
    ä¹ĭä¸Ģ
    -0.06
    restrict
    -0.06
    gis
    -0.06
     DISPATCH
    -0.06
    lash
    -0.06
    POSITIVE LOGITS
     pilots
    0.07
    eker
    0.07
    ihar
    0.06
     conven
    0.06
     Bas
    0.06
     teased
    0.06
    quarter
    0.06
     captures
    0.06
     pilot
    0.06
    )(((
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.