© 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 EvalsExportsAPI 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. 84366
    Prev
    Next
    INDEX
    Explanations

    citations or references in a text

    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
     ìŀĶ
    -0.07
    eda
    -0.06
    FRING
    -0.06
    oris
    -0.06
     Software
    -0.06
    blr
    -0.06
    isNull
    -0.06
     Grinder
    -0.06
    dag
    -0.06
    ìħ
    -0.06
    POSITIVE LOGITS
     gi
    0.07
    coli
    0.06
     Division
    0.06
     fitting
    0.06
    _arrow
    0.06
    iales
    0.06
     WARRANT
    0.06
     neutral
    0.06
    494
    0.06
     vector
    0.06
    Activations Density 0.000%

    No Known Activations