© 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. 4626
    Prev
    Next
    INDEX
    Explanations

    variables and data properties related to graphics or interface elements in coding contexts

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

    C++ type identifiers and modifiers in function signatures, particularly "shared_str" (shared string type) and unsigned integer types ("u8", "u16", "u32") used in parameter declarations.

    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
    avana
    -0.07
    errick
    -0.06
    rouch
    -0.06
    loh
    -0.06
    avors
    -0.06
    év
    -0.06
     dane
    -0.06
    avn
    -0.06
    utive
    -0.06
    marvin
    -0.05
    POSITIVE LOGITS
    onna
    0.07
    istica
    0.07
    ĴĮ
    0.06
    arya
    0.06
    issant
    0.06
    stru
    0.06
     PMC
    0.06
    str
    0.06
    ZZ
    0.06
    icast
    0.06
    Activations Density 0.092%

    No Known Activations