© 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. 18304
    Prev
    Next
    INDEX
    Explanations

    ethical dilemmas and moral implications

    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
    retty
    -0.06
    дем
    -0.06
    ucci
    -0.06
    еÑĢе
    -0.06
    ÎķÎĻ
    -0.06
    riel
    -0.06
    .sc
    -0.06
    cca
    -0.06
    cker
    -0.06
    تر
    -0.06
    POSITIVE LOGITS
    -thumbnails
    0.07
     rowspan
    0.07
    otu
    0.07
    evenodd
    0.06
    sembl
    0.06
    \Redirect
    0.06
    ahas
    0.06
     [âĢ¦]↵↵
    0.06
    -unstyled
    0.06
     CreateMap
    0.06
    Activations Density 0.004%

    No Known Activations