© 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. 40280
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and places

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

    The letter sequence "el" appearing within words, names, and abbreviations across different languages and contexts.

    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
    ess
    -0.12
    yonel
    -0.12
    elli
    -0.12
    em
    -0.11
    ex
    -0.11
    ell
    -0.11
    es
    -0.11
    elle
    -0.11
    ed
    -0.11
    el
    -0.10
    POSITIVE LOGITS
    abyrinth
    0.12
    ateral
    0.12
    iferay
    0.11
    orraine
    0.11
    ts
    0.11
    izabeth
    0.11
    icious
    0.11
    ty
    0.11
    abyrin
    0.10
    ighthouse
    0.10
    Activations Density 1.255%

    No Known Activations