© 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. 15-LLAMASCOPE-RES-131K
    11. 27483
    Prev
    Next
    INDEX
    Explanations

    pronouns and common linking words

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

    Common function words and pronouns that appear in conversational text, often within quotes or personal narratives.

    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
    inders
    -0.06
    r
    -0.06
    ed
    -0.06
    ãĥĥãĥĹ
    -0.06
    rips
    -0.06
    us
    -0.06
    it
    -0.06
    i
    -0.06
    AMP
    -0.06
    p
    -0.05
    POSITIVE LOGITS
    IFn
    0.07
    ippo
    0.07
    MLS
    0.07
    uvw
    0.07
    EDIATE
    0.07
    ì§Ī
    0.07
    bedo
    0.07
    yne
    0.07
    WXYZ
    0.07
    OLLOW
    0.07
    Activations Density 0.007%

    No Known Activations