© 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. 15-LLAMASCOPE-RES-131K
    11. 62331
    Prev
    Next
    INDEX
    Explanations

    elements related to coding parameters and settings in software documentation

    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
    iola
    -0.07
    åłĤ
    -0.07
    UGE
    -0.07
    itr
    -0.07
    errat
    -0.06
     hend
    -0.06
    ordon
    -0.06
     ثبت
    -0.06
    _CANNOT
    -0.06
     Cooke
    -0.06
    POSITIVE LOGITS
     optional
    0.28
    optional
    0.25
     OPTIONAL
    0.22
     Optional
    0.22
    (optional
    0.21
    Optional
    0.21
    _optional
    0.17
     optionally
    0.17
    .optional
    0.17
    (Optional
    0.16
    Activations Density 0.154%

    No Known Activations