© 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 EvalsExportsAPI 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. 106567
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate distance or proximity

    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
     Marty
    -0.07
    ascimento
    -0.06
     newRow
    -0.06
     Movement
    -0.06
    ='".
    -0.06
     weight
    -0.06
    .IContainer
    -0.06
     Nice
    -0.06
     Deb
    -0.06
    ùa
    -0.06
    POSITIVE LOGITS
    rok
    0.09
    lant
    0.07
    Scaler
    0.07
     îł
    0.06
    иÑı
    0.06
     nowhere
    0.06
    estate
    0.06
    reck
    0.06
    odd
    0.06
     estate
    0.06
    Activations Density 0.007%

    No Known Activations