© 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. 1192
    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
    ansi
    -0.07
     hit
    -0.07
     host
    -0.06
     accidentally
    -0.06
    815
    -0.06
     Skinner
    -0.06
    -0.06
     Anc
    -0.06
     wallet
    -0.06
     Seal
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.08
    lacak
    0.07
    oman
    0.07
    ICODE
    0.07
     ragaz
    0.07
    iming
    0.07
    overall
    0.07
    çļĦä¸Ģ个
    0.07
     tzv
    0.07
     ëĺIJ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.