© 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 EvalsExportsAPI 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. 75105
    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
     Fan
    -0.06
    amat
    -0.06
     milling
    -0.06
    adius
    -0.05
     com
    -0.05
    zy
    -0.05
     fandom
    -0.05
     Prim
    -0.05
    atter
    -0.05
     Bd
    -0.05
    POSITIVE LOGITS
    кÑģ
    0.08
    errick
    0.08
    WARDS
    0.07
    Ups
    0.07
    ụn
    0.07
    UnderTest
    0.06
     *)((
    0.06
    èĺ
    0.06
    ãĥ³ãĥĩ
    0.06
    Bundle
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.