© 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. 1765
    Prev
    Next
    INDEX
    Explanations

    content related to proofreading and grammar checking

    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
    oplast
    -0.06
    ÑĤаÑħ
    -0.06
    eph
    -0.06
     çĤ
    -0.06
    yii
    -0.06
    صÙĦ
    -0.06
    íıī
    -0.06
    mf
    -0.06
     mnemonic
    -0.06
    ÙĪØŃ
    -0.06
    POSITIVE LOGITS
     errors
    0.14
     error
    0.13
     miss
    0.12
     Errors
    0.11
    _errors
    0.10
    errors
    0.10
     errores
    0.10
    -errors
    0.10
     mistakes
    0.10
    Errors
    0.10
    Activations Density 0.058%

    No Known Activations