© 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. 129725
    Prev
    Next
    INDEX
    Explanations

    syntax structures and formatting in programming code

    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
    ler
    -0.08
    vel
    -0.07
    acial
    -0.07
    archy
    -0.07
    ilit
    -0.07
    âĢ¦↵↵↵
    -0.07
    \grid
    -0.07
    mes
    -0.07
    ons
    -0.07
    rel
    -0.06
    POSITIVE LOGITS
    ÌĨ
    0.09
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.07
    ì²ľ
    0.07
     ÑģобоÑİ
    0.06
    forth
    0.06
    /he
    0.06
    echa
    0.06
    fts
    0.06
    .ibm
    0.06
    hue
    0.06
    Activations Density 0.170%

    No Known Activations