© 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. 79470
    Prev
    Next
    INDEX
    Explanations

    instances of shocking or disturbing content

    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
     crossword
    -0.07
    val
    -0.06
    andom
    -0.06
    ahn
    -0.06
    ann
    -0.06
    ansi
    -0.06
     Hir
    -0.06
     PW
    -0.05
     trade
    -0.05
    Printf
    -0.05
    POSITIVE LOGITS
     shown
    0.13
    shown
    0.12
     video
    0.10
    è§Ĩé¢ij
    0.09
     videa
    0.09
     vidéo
    0.09
     footage
    0.09
    Shown
    0.08
     clip
    0.08
     кад
    0.08
    Activations Density 0.010%

    No Known Activations