© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27174
    Prev
    Next
    INDEX
    Explanations

    references to specific numbers and associated configurations

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

    Small text fragments that appear within structured technical content like code, XML, bibliographic entries, or mathematical notation.

    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
    et
    -0.08
    eten
    -0.08
     Hunger
    -0.07
    eton
    -0.06
    pn
    -0.06
    hti
    -0.06
    yen
    -0.06
    ijk
    -0.06
    qa
    -0.06
    apan
    -0.06
    POSITIVE LOGITS
     aforementioned
    0.07
    ivet
    0.07
    kker
    0.07
    ÑĤап
    0.07
    bote
    0.07
     Banc
    0.06
    æĸĹ
    0.06
    _iface
    0.06
    bilt
    0.06
    .Hosting
    0.06
    Activations Density 0.030%

    No Known Activations