© 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. 70237
    Prev
    Next
    INDEX
    Explanations

    actions or conditions that describe the successful execution or proper handling of tasks

    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
    enet
    -0.07
    ierge
    -0.07
     PROGMEM
    -0.07
    ÃľM
    -0.07
    tera
    -0.07
    .Txt
    -0.07
    Äįet
    -0.07
    RootElement
    -0.06
    udit
    -0.06
    nero
    -0.06
    POSITIVE LOGITS
    maal
    0.06
     properly
    0.06
    éģĩ
    0.06
    asan
    0.06
    Tube
    0.06
    Extras
    0.06
    fang
    0.06
     unstoppable
    0.05
    gov
    0.05
    aph
    0.05
    Activations Density 0.037%

    No Known Activations