© 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. 2308
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and political figures

    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
    quares
    -0.07
    (Optional
    -0.07
    ypical
    -0.07
    agina
    -0.06
    enties
    -0.06
    داÙĨÙĦÙĪد
    -0.06
    endez
    -0.06
    thood
    -0.06
    NÄ°
    -0.06
    otte
    -0.06
    POSITIVE LOGITS
    [".
    0.06
    ihan
    0.06
     amac
    0.06
    enberg
    0.06
    ECT
    0.06
    åı·
    0.06
    EmptyEntries
    0.06
    çļĦå£°éŁ³
    0.06
    =”
    0.06
    太éĥİ
    0.06
    Activations Density 0.037%

    No Known Activations