© 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. 1109
    Prev
    Next
    INDEX
    Explanations

    references to specific programming functions or components

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

    Function words and connectors (especially the article "a") that bridge technical concepts in academic, programming, and descriptive 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
    ãĤ¡
    -0.07
    emes
    -0.06
    ãĤ£
    -0.06
    lund
    -0.06
    ornings
    -0.06
     bir
    -0.06
     odst
    -0.06
     دار
    -0.06
     sans
    -0.05
    assis
    -0.05
    POSITIVE LOGITS
    .nano
    0.08
     '../../../../../
    0.07
    ®
    0.06
    CLUDED
    0.06
    utedString
    0.06
    ameda
    0.06
    åĦ
    0.06
    OLDER
    0.06
     azi
    0.06
    692
    0.06
    Activations Density 0.160%

    No Known Activations