© 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. 15-LLAMASCOPE-RES-131K
    11. 103455
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or request for something

    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
    екÑĥ
    -0.07
    lä
    -0.06
    ill
    -0.06
    çķ
    -0.06
    ort
    -0.06
    ovat
    -0.06
     Curse
    -0.06
    tÄĽ
    -0.06
    ough
    -0.06
    ane
    -0.06
    POSITIVE LOGITS
    icontrol
    0.09
    à¸Ļà¸ķ
    0.08
    oog
    0.08
    ãĥ¼ãĥŃ
    0.07
    utral
    0.07
    abbo
    0.07
     tang
    0.07
    .jquery
    0.07
    ãĥ«ãĤ¯
    0.07
    à¸Ķาว
    0.07
    Activations Density 0.000%

    No Known Activations