© 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. 17821
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Brett."

    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
    ร
    -0.08
    รร
    -0.07
    IED
    -0.07
    rn
    -0.07
    Ïħκ
    -0.07
    ibir
    -0.07
    erland
    -0.07
    gor
    -0.06
    querque
    -0.06
    _hooks
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.07
    leur
    0.07
    lich
    0.07
    ician
    0.07
    365
    0.07
    sdale
    0.07
    ails
    0.06
    ler
    0.06
    ailability
    0.06
     dissip
    0.06
    Activations Density 0.001%

    No Known Activations