© 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 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. 74797
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, indicating a focus on specific individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Names or terms of address used when directly speaking to or referring to a specific person or group in text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ournal
    -0.08
    ibt
    -0.08
    èķī
    -0.08
    âĢ¦"↵↵
    -0.07
    еком
    -0.07
    ocre
    -0.07
    .cljs
    -0.07
    ágina
    -0.07
    ладÑĥ
    -0.07
    feit
    -0.07
    POSITIVE LOGITS
    ;
    0.07
    ale
    0.07
    !
    0.06
    .
    0.06
    .↵
    0.06
    ali
    0.06
     sir
    0.06
    itz
    0.06
    ,↵
    0.06
    asi
    0.06
    Activations Density 0.035%

    No Known Activations