© 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. 94410
    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
    ople
    -0.07
    813
    -0.06
    815
    -0.06
    ô
    -0.06
    _lineno
    -0.06
    abwe
    -0.06
    пÑĢиклад
    -0.06
    337
    -0.06
    brick
    -0.06
    POSITIVE LOGITS
    edly
    0.07
     meanwhile
    0.06
    ).__
    0.06
    olf
    0.06
     aforementioned
    0.06
     dabei
    0.06
    _bm
    0.06
    chw
    0.06
    ');"
    0.06
     seiz
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.