© 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. 17-LLAMASCOPE-RES-131K
    11. 58097
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions, results, and descriptions of actions or states

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

    Adverbs and adverbial expressions that modify statements by indicating time, certainty, location, or qualification of the main assertion.

    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
    Č
    -0.09
    -0.07
     Swinger
    -0.07
    ãĥ³ãĥĨãĤ£
    -0.07
    abilit
    -0.07
    ervo
    -0.07
    whereIn
    -0.07
    Ñĭл
    -0.07
     коÑĤоÑĢ
    -0.07
    InSection
    -0.07
    POSITIVE LOGITS
    ike
    0.07
    ">//
    0.06
     unc
    0.06
    wise
    0.06
    vero
    0.06
    mouseup
    0.06
    iola
    0.05
    uppen
    0.05
    ï¸ı
    0.05
    .
    0.05
    Activations Density 0.194%

    No Known Activations