© 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. 2144
    Prev
    Next
    INDEX
    Explanations

    the presence of the substring "stit"

    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
    asn
    -0.06
    anou
    -0.06
    erts
    -0.06
    ">//
    -0.06
    hek
    -0.06
    iors
    -0.06
    ±
    -0.06
    oti
    -0.06
    itto
    -0.06
    retch
    -0.06
    POSITIVE LOGITS
    üp
    0.07
    &action
    0.06
    phe
    0.06
    upert
    0.06
    OTH
    0.06
    usp
    0.06
    tro
    0.06
    ç°
    0.06
    оÑĢож
    0.06
    δή
    0.06
    Activations Density 0.000%

    No Known Activations