© 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. 106267
    Prev
    Next
    INDEX
    Explanations

    locations and institutions of interest that may attract visitors

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

    Grammatical connecting elements (like forms of "to be", conjunctions, and prepositions) that establish relationships between subjects and their descriptions, particularly in content about locations or properties.

    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
    éĽij
    -0.07
    noop
    -0.07
    igan
    -0.06
    éĬ
    -0.06
    èģĶç½ij
    -0.06
     Roo
    -0.06
    èĭĹ
    -0.06
    تب
    -0.06
    [rand
    -0.06
    241
    -0.06
    POSITIVE LOGITS
    aret
    0.07
     famous
    0.07
    meden
    0.07
    ugar
    0.07
    kker
    0.07
     famously
    0.06
    oriously
    0.06
     iconic
    0.06
    sse
    0.06
    chez
    0.06
    Activations Density 0.009%

    No Known Activations