© 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. 15307
    Prev
    Next
    INDEX
    Explanations

    programming syntax and 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
    icket
    -0.07
    CastException
    -0.07
     scarc
    -0.07
    luvÃŃ
    -0.06
    osy
    -0.06
    indsight
    -0.06
    getc
    -0.06
    illions
    -0.06
    amos
    -0.06
    éĬ
    -0.06
    POSITIVE LOGITS
    лава
    0.07
     Bian
    0.06
     Wet
    0.06
     exped
    0.06
     Vet
    0.06
     заÑĤ
    0.06
     Ket
    0.06
     Lay
    0.06
    .basic
    0.05
    _ssl
    0.05
    Activations Density 0.010%

    No Known Activations