© 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. 117414
    Prev
    Next
    INDEX
    Explanations

    email addresses and contact information

    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
    ultipart
    -0.07
    Ñıб
    -0.07
    amma
    -0.07
    unca
    -0.07
    ppo
    -0.07
    .Handled
    -0.07
    âu
    -0.07
    lesson
    -0.07
    ạ
    -0.06
     Narrow
    -0.06
    POSITIVE LOGITS
     pr
    0.08
     press
    0.07
     media
    0.06
     Establishment
    0.06
    resse
    0.06
     thumb
    0.06
     pool
    0.06
    PR
    0.06
     proportional
    0.06
     others
    0.06
    Activations Density 0.004%

    No Known Activations