© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90862
    Prev
    Next
    INDEX
    Explanations

    references to ongoing processes and actions

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

    Punctuation marks and common words appearing in structured text, particularly periods after scale measurements in geological map citations.

    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
    abin
    -0.07
    ¦
    -0.07
    Versions
    -0.06
    raq
    -0.06
    à¸Ĺาà¸Ļ
    -0.06
    ardon
    -0.06
    pora
    -0.06
     gent
    -0.06
    лагод
    -0.06
    apons
    -0.05
    POSITIVE LOGITS
     Kas
    0.06
    ugas
    0.06
    aminer
    0.06
    andr
    0.06
    rzy
    0.06
    ört
    0.06
     also
    0.06
    ummies
    0.06
    GMEM
    0.06
    llx
    0.06
    Activations Density 0.025%

    No Known Activations