© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 88982
    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
     abl
    -0.06
    ä¸Ģç§į
    -0.06
    bib
    -0.06
    CurrentValue
    -0.06
    akit
    -0.06
     discord
    -0.06
     Laurent
    -0.05
    inas
    -0.05
    iek
    -0.05
    platz
    -0.05
    POSITIVE LOGITS
    _mD
    0.07
    munition
    0.07
    endoza
    0.07
    mazon
    0.07
    ÙģاÙĤ
    0.07
     fwd
    0.07
    _mE
    0.07
    lena
    0.07
    -lnd
    0.07
    acula
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.