© 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. 69482
    Prev
    Next
    INDEX
    Explanations

    references to the devil and related concepts

    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
    emean
    -0.08
    eway
    -0.08
    sob
    -0.07
    exual
    -0.07
    uncan
    -0.06
    IDL
    -0.06
    une
    -0.06
    eworld
    -0.06
    iciel
    -0.06
    -navbar
    -0.06
    POSITIVE LOGITS
    ishly
    0.10
    bane
    0.09
    gram
    0.07
    oni
    0.07
    /null
    0.07
    OutOfRange
    0.07
    ution
    0.07
    ry
    0.07
    UTION
    0.07
    /dev
    0.07
    Activations Density 0.004%

    No Known Activations