© 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. 2337
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and programming constructs

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

    Technical code elements, syntax structures, and programming terminology that are crucial for correct implementation in software development.

    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
    inox
    -0.08
    edla
    -0.08
    antt
    -0.08
    خاÙĨ
    -0.07
    _pan
    -0.07
    aeper
    -0.07
    antium
    -0.07
    theid
    -0.06
    ãĥ³ãĥĩãĤ£
    -0.06
    anitize
    -0.06
    POSITIVE LOGITS
     autocomplete
    0.12
     suggestions
    0.11
     suggestion
    0.11
    autocomplete
    0.11
     Aut
    0.10
    Completion
    0.10
     completion
    0.10
    Suggestions
    0.10
    Aut
    0.10
    completion
    0.09
    Activations Density 0.053%

    No Known Activations