© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 27652
    Prev
    Next
    INDEX
    Explanations

    definitions and discussions of concepts

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

    Punctuation marks (primarily periods) that end sentences, often followed by the beginning of new sentences, particularly in contexts where definitions or explanations are being provided.

    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
     kurul
    -0.06
     Famil
    -0.06
    irt
    -0.06
    stdcall
    -0.06
    oui
    -0.06
    ий
    -0.06
    ordinal
    -0.06
    intel
    -0.06
    ival
    -0.06
    elez
    -0.05
    POSITIVE LOGITS
     definition
    0.25
     definitions
    0.23
    definition
    0.21
     Definition
    0.21
    definitions
    0.19
    -definition
    0.19
    Definition
    0.19
     Definitions
    0.19
    Definitions
    0.18
    _definition
    0.17
    Activations Density 0.073%

    No Known Activations