© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 41669
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to organizations or programs

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

    The text shows examples of acronyms or abbreviations explained with phrases like "stands for" or preceded by words like "is" or a comma introducing the full form. Often these explanations follow organizational names (PCC, NEET, SSN), project names (M4-health), or technical terms, and sometimes appear in parenthetical explanations.

    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
     Andreas
    -0.06
    iset
    -0.06
     Stripe
    -0.06
     Cant
    -0.06
    .gs
    -0.05
    stra
    -0.05
     Ferd
    -0.05
    776
    -0.05
     Moreno
    -0.05
    cak
    -0.05
    POSITIVE LOGITS
     acronym
    0.24
     stands
    0.22
    stands
    0.20
     abbreviation
    0.20
     stand
    0.19
     stood
    0.19
    abbreviation
    0.18
     Stand
    0.17
     standing
    0.16
     initials
    0.16
    Activations Density 0.106%

    No Known Activations