© 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. 126486
    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
    迹
    -0.07
    oria
    -0.07
    ati
    -0.07
    aeper
    -0.07
    ãĥ¼ãĤ¹ãĥĪ
    -0.07
    raquo
    -0.06
     buurt
    -0.06
    apid
    -0.06
     neighbourhood
    -0.06
    cplusplus
    -0.06
    POSITIVE LOGITS
     amac
    0.06
    .jasper
    0.06
    iqué
    0.06
    Zen
    0.06
     carte
    0.06
    .libs
    0.06
    ollen
    0.06
    zen
    0.06
    cratch
    0.06
    aley
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.