© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84725
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific variable names or identifiers in programming language syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ellation
    -0.07
    Ø´Ùħ
    -0.07
    ftware
    -0.06
    edii
    -0.06
    è¬
    -0.06
    agation
    -0.06
    ãĤ«ãĥĨ
    -0.06
    elib
    -0.06
    kinson
    -0.06
    unta
    -0.06
    POSITIVE LOGITS
    unks
    0.06
    TTY
    0.06
    IID
    0.06
    260
    0.06
    apt
    0.06
    sad
    0.06
    APT
    0.06
    è¼
    0.06
    egis
    0.06
    ek
    0.06
    Activations Density 0.014%

    No Known Activations