© 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. 9-LLAMASCOPE-RES-131K
    11. 94484
    Prev
    Next
    INDEX
    Explanations

    references to council meetings and decisions

    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
    amente
    -0.07
    .dtd
    -0.07
    panies
    -0.07
    zego
    -0.07
    unami
    -0.07
    enga
    -0.06
    ĵåIJį
    -0.06
    IMPLIED
    -0.06
    è®®
    -0.06
    alsex
    -0.06
    POSITIVE LOGITS
     Moral
    0.07
    asso
    0.06
    pseudo
    0.06
    stal
    0.06
    ->{
    0.06
    heck
    0.06
    rozen
    0.06
    cheng
    0.06
     Vik
    0.06
    Ñīее
    0.06
    Activations Density 0.006%

    No Known Activations