© 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. 117508
    Prev
    Next
    INDEX
    Explanations

    code related to creating and manipulating data structures, particularly arrays

    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
    istring
    -0.08
    _Null
    -0.08
    atrix
    -0.07
     atan
    -0.07
    ictim
    -0.07
    -urlencoded
    -0.07
    .tencent
    -0.07
     rotated
    -0.07
    utow
    -0.07
    inson
    -0.06
    POSITIVE LOGITS
     integer
    0.10
     GLsizei
    0.09
     Integer
    0.09
    <number
    0.09
    Integer
    0.08
     int
    0.08
    integer
    0.08
     numeric
    0.07
     INTEGER
    0.07
    <size
    0.07
    Activations Density 0.213%

    No Known Activations