© 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. 80952
    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
    archives
    -0.07
     ‘
    -0.06
    fan
    -0.06
    atica
    -0.05
    ikan
    -0.05
    etti
    -0.05
    <>
    -0.05
    .hm
    -0.05
    PIO
    -0.05
     tro
    -0.05
    POSITIVE LOGITS
    inish
    0.07
    unden
    0.07
    storybook
    0.07
    дом
    0.07
    ,assign
    0.07
    amil
    0.06
    _BS
    0.06
    ãĥ³ãĥĨãĤ£
    0.06
     BuzzFeed
    0.06
    ilit
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.