© 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. 74967
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their contexts in 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
    iesen
    -0.08
    ectl
    -0.07
    eling
    -0.07
    uire
    -0.07
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.06
    okud
    -0.06
    âĢ¦.↵↵
    -0.06
    εÏģÏĮ
    -0.06
    urai
    -0.06
    uve
    -0.06
    POSITIVE LOGITS
    -----------*/↵
    0.08
    quina
    0.07
    úmeros
    0.06
    MethodInfo
    0.06
    NP
    0.06
    oloj
    0.06
    adow
    0.06
    ulle
    0.06
     orient
    0.06
    Ñĩай
    0.06
    Activations Density 0.002%

    No Known Activations