© 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. 108377
    Prev
    Next
    INDEX
    Explanations

    adjectives expressing preference or superiority

    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
    apter
    -0.07
    ism
    -0.07
     more
    -0.07
    beck
    -0.07
    μÎŃ
    -0.07
    kt
    -0.06
    geois
    -0.06
    dition
    -0.06
    edis
    -0.06
     resp
    -0.06
    POSITIVE LOGITS
    seller
    0.10
    /all
    0.08
    /fast
    0.08
    igators
    0.07
    stay
    0.07
    HeaderCode
    0.07
    ijn
    0.06
    UserCode
    0.06
    'icon
    0.06
    ï¸ı
    0.06
    Activations Density 0.004%

    No Known Activations