© 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. 15214
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets used in code structures

    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
    681
    -0.06
    chez
    -0.06
    atto
    -0.06
    ection
    -0.06
    uy
    -0.06
    uat
    -0.06
    letion
    -0.06
    619
    -0.06
    uet
    -0.06
    ró
    -0.06
    POSITIVE LOGITS
     Merk
    0.06
    -fw
    0.06
    mah
    0.06
    Ñģок
    0.06
    маÑħ
    0.06
    اسÙĩ
    0.06
     fora
    0.06
    ses
    0.06
     Burnett
    0.06
     sunshine
    0.06
    Activations Density 0.004%

    No Known Activations