© 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. 17-LLAMASCOPE-RES-131K
    11. 41289
    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
     $
    -0.07
    ifen
    -0.07
    apture
    -0.06
    /gin
    -0.06
    -cols
    -0.06
    aho
    -0.06
    jeta
    -0.06
    uky
    -0.06
     Merc
    -0.06
     Fol
    -0.06
    POSITIVE LOGITS
    -sama
    0.07
    fh
    0.06
    igmoid
    0.06
    andbox
    0.06
    isbury
    0.06
    ervlet
    0.06
    ially
    0.06
    -chan
    0.06
    íĹĮ
    0.06
    mil
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.