© 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. 92951
    Prev
    Next
    INDEX
    Explanations

    references to methods and methodology in various contexts

    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
     forth
    -0.08
    onnement
    -0.07
    MSC
    -0.07
    ın
    -0.06
    itol
    -0.06
    erç
    -0.06
    BN
    -0.06
     seedu
    -0.06
    avad
    -0.06
    !=(
    -0.06
    POSITIVE LOGITS
    ical
    0.07
    alsa
    0.07
    ccb
    0.07
    urette
    0.07
    agua
    0.07
    ÙĨج
    0.07
    tic
    0.07
    HEL
    0.06
     Bookmark
    0.06
    qua
    0.06
    Activations Density 0.010%

    No Known Activations