© 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 EvalsExportsinterp-engineNEWAPI 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. 105257
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     اÙĦبÙĦد
    -0.06
    chest
    -0.06
    sonian
    -0.06
    âĢ¦
    -0.06
    uper
    -0.05
     Vic
    -0.05
    .constructor
    -0.05
    cient
    -0.05
    ometown
    -0.05
     Shine
    -0.05
    POSITIVE LOGITS
     EOF
    0.09
    ONUS
    0.09
     @}
    0.09
     sourceMappingURL
    0.08
     eof
    0.08
    END
    0.08
    egend
    0.08
    zdy
    0.08
     nackte
    0.08
    ADED
    0.08
    Activations Density 0.012%

    No Known Activations