© 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. 73492
    Prev
    Next
    INDEX
    Explanations

    mentions of notable or famous individuals with specific names

    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
    eken
    -0.08
    bole
    -0.07
    «a
    -0.07
    ockey
    -0.07
    phia
    -0.07
    closure
    -0.07
     Segment
    -0.06
    cação
    -0.06
    *>(&
    -0.06
    emes
    -0.06
    POSITIVE LOGITS
     Zug
    0.07
     {{{
    0.06
     Crimson
    0.06
     Alv
    0.06
    671
    0.06
    qu
    0.06
    rig
    0.06
     Silva
    0.06
     IEntity
    0.06
     ties
    0.06
    Activations Density 0.000%

    No Known Activations