© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15852
    Prev
    Next
    INDEX
    Explanations

    statements expressing problems or challenges

    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
     mean
    -0.07
    ilogy
    -0.07
    etter
    -0.07
    arcy
    -0.07
    das
    -0.07
     une
    -0.06
    ez
    -0.06
    tod
    -0.06
    adesh
    -0.06
    avenport
    -0.06
    POSITIVE LOGITS
    ABCDEFGHIJKLMNOP
    0.07
    none
    0.07
    abelle
    0.07
    .getAs
    0.07
    elian
    0.06
    >{@
    0.06
    ABEL
    0.06
    NONE
    0.06
    olen
    0.06
     Lans
    0.06
    Activations Density 0.015%

    No Known Activations