© 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 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. 17-LLAMASCOPE-RES-131K
    6. 88542
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with quality or condition

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

    Words that represent specific technical or domain-specialized terms, including: programming variables/properties (normal, partial, vanced, intensive), food preparation terms (puree), descriptive adjectives (Small, Little, Wrong, Bright, Short, blind, bad), and other technical terminology that appears in specialized contexts.

    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
    frei
    -0.09
    /xhtml
    -0.08
    IFORM
    -0.08
    eln
    -0.08
    šti
    -0.08
    گر
    -0.07
    bers
    -0.07
    istrovstvÃŃ
    -0.07
    holes
    -0.07
    -INF
    -0.07
    POSITIVE LOGITS
    mente
    0.12
    ness
    0.11
    ities
    0.11
    ity
    0.10
    most
    0.10
    NESS
    0.09
    -handed
    0.08
    bred
    0.07
    æ´²
    0.07
    zeitig
    0.07
    Activations Density 0.352%

    No Known Activations