© 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. 9-LLAMASCOPE-RES-131K
    11. 97642
    Prev
    Next
    INDEX
    Explanations

    details related to scientific methodologies and their comparisons

    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
    oud
    -0.06
    ecal
    -0.06
    ihar
    -0.06
     Clarke
    -0.05
    declare
    -0.05
    ús
    -0.05
    eso
    -0.05
    ieg
    -0.05
     particularly
    -0.05
    qui
    -0.05
    POSITIVE LOGITS
    lyph
    0.07
     obed
    0.07
    riet
    0.07
    ogie
    0.07
     Mezi
    0.06
    иком
    0.06
    okie
    0.06
    astes
    0.06
     Mey
    0.06
     示
    0.06
    Activations Density 0.263%

    No Known Activations