© 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. 62362
    Prev
    Next
    INDEX
    Explanations

    instances of character names and their interactions

    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
     blinked
    -0.08
     blink
    -0.08
    blink
    -0.07
     blinking
    -0.07
    Frame
    -0.06
     Reynolds
    -0.06
    544
    -0.06
    rames
    -0.05
     trailed
    -0.05
    POS
    -0.05
    POSITIVE LOGITS
     masses
    0.08
    vang
    0.07
    kowski
    0.07
    toJson
    0.07
    dess
    0.07
    zek
    0.07
     prim
    0.07
    stanov
    0.07
    ippers
    0.07
    akedown
    0.07
    Activations Density 0.017%

    No Known Activations