© 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. 79752
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements in text

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

    Code delimiters used in print/debug statements across different programming languages to mark the beginning of output sections or to format console messages.

    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
    in
    -0.07
    /
    -0.07
    r
    -0.07
    uc
    -0.06
    f
    -0.06
     Knights
    -0.06
    ler
    -0.06
    b
    -0.06
    is
    -0.06
    éī
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    EPHIR
    0.08
    htar
    0.08
    _TAC
    0.08
    .LookAndFeel
    0.08
    ColumnsMode
    0.07
    skirts
    0.07
    IIIK
    0.07
    usercontent
    0.07
    phies
    0.07
    Activations Density 0.028%

    No Known Activations