© 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. 104876
    Prev
    Next
    INDEX
    Explanations

    discussions around societal and behavioral issues related to violence and responsibility

    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
     during
    -0.09
     when
    -0.08
     lors
    -0.08
     after
    -0.08
    _when
    -0.08
     dopo
    -0.08
     durante
    -0.07
     cuando
    -0.07
     recent
    -0.07
     когда
    -0.07
    POSITIVE LOGITS
    ãģļ
    0.06
    íĥĢ
    0.06
    259
    0.06
     again
    0.06
    arg
    0.06
    ác
    0.06
    again
    0.06
     Seam
    0.06
     novamente
    0.06
    psilon
    0.06
    Activations Density 0.268%

    No Known Activations