© 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. 60211
    Prev
    Next
    INDEX
    Explanations

    conjunctions, particularly the word "and" used frequently in various contexts

    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
     Sparks
    -0.06
    aque
    -0.06
    apos
    -0.06
    až
    -0.06
    .met
    -0.06
    issen
    -0.06
    ynchronized
    -0.06
    енÑģ
    -0.06
    rowsable
    -0.06
    phans
    -0.06
    POSITIVE LOGITS
    hton
    0.07
    iete
    0.07
    iqueta
    0.07
    ãĥ¼ãĥį
    0.07
    _CONTINUE
    0.07
    odem
    0.06
    ona
    0.06
    IPHER
    0.06
     lod
    0.06
    dera
    0.06
    Activations Density 0.056%

    No Known Activations