© 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. 55027
    Prev
    Next
    INDEX
    Explanations

    references to data, including its properties and operations

    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
    _INCLUDED
    -0.07
    Å¡ka
    -0.07
    oton
    -0.06
    hea
    -0.06
    rena
    -0.06
    sic
    -0.06
    زر
    -0.06
    _UNIQUE
    -0.06
    cmc
    -0.06
    asy
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
    mediately
    0.06
    ControlEvents
    0.06
    .scalablytyped
    0.06
    azon
    0.06
    oji
    0.06
    uste
    0.06
    eczy
    0.06
    inan
    0.06
    tier
    0.06
    Activations Density 0.042%

    No Known Activations