© 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. 86656
    Prev
    Next
    INDEX
    Explanations

    references to video content, tips, and various attack patterns in discussions

    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
     kanal
    -0.07
     tabi
    -0.07
    WithPath
    -0.07
    еÑģÑı
    -0.06
    uckets
    -0.06
    ĺIJ
    -0.06
    Views
    -0.06
    olean
    -0.06
    íħ
    -0.06
     ç¿
    -0.06
    POSITIVE LOGITS
     #
    0.09
    ensor
    0.06
     @
    0.06
    @Id
    0.06
     Bund
    0.06
     âĦĸ
    0.06
     &
    0.06
    ally
    0.06
    ="
    0.06
    ména
    0.06
    Activations Density 0.033%

    No Known Activations