© 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 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. 56088
    Prev
    Next
    INDEX
    Explanations

    lines of code related to console output in a programming context

    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
    achuset
    -0.07
    del
    -0.06
    ipl
    -0.06
    court
    -0.06
    ÙĪÙĤ
    -0.06
    point
    -0.06
    liest
    -0.06
    SI
    -0.06
    ej
    -0.06
    guard
    -0.06
    POSITIVE LOGITS
    -speaking
    0.08
    UGH
    0.07
    avigator
    0.07
     Lem
    0.06
    ãĤ¯ãĥĪ
    0.06
    arend
    0.06
    iqueta
    0.06
    ừa
    0.06
    ConverterFactory
    0.06
    egration
    0.06
    Activations Density 0.011%

    No Known Activations