© 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. 105420
    Prev
    Next
    INDEX
    Explanations

    references to legendary or mythological figures, particularly Hercules

    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
    celik
    -0.08
    ri
    -0.08
    omy
    -0.08
    .InnerException
    -0.07
    omanip
    -0.07
    lili
    -0.07
    rieb
    -0.07
    á»ģ
    -0.07
    ventus
    -0.07
    radi
    -0.07
    POSITIVE LOGITS
    et
    0.07
    vet
    0.07
    ing
    0.06
    ug
    0.06
    nbsp
    0.06
     Taste
    0.06
    er
    0.06
    ilha
    0.06
    yn
    0.06
    esco
    0.06
    Activations Density 0.044%

    No Known Activations