© 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. 15-LLAMASCOPE-RES-131K
    11. 86373
    Prev
    Next
    INDEX
    Explanations

    numerical references related to episodes in a series

    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
    itics
    -0.06
    ÑĥÑĢÑģ
    -0.06
    854
    -0.06
     hypers
    -0.06
     Urb
    -0.06
     synth
    -0.06
     geb
    -0.06
    umor
    -0.05
    colon
    -0.05
    .getSelection
    -0.05
    POSITIVE LOGITS
    otas
    0.07
    jas
    0.07
    swift
    0.06
    äºŃ
    0.06
     Encore
    0.06
    WithString
    0.06
    eken
    0.06
    MY
    0.06
    recision
    0.06
    .fx
    0.06
    Activations Density 0.001%

    No Known Activations