© 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. 73553
    Prev
    Next
    INDEX
    Explanations

    references to prominent publications or literary accolades

    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
    ogle
    -0.07
    handlers
    -0.07
    olate
    -0.07
    uled
    -0.07
    olation
    -0.07
    ulu
    -0.06
    bern
    -0.06
    hani
    -0.06
    oji
    -0.06
     Party
    -0.06
    POSITIVE LOGITS
    urat
    0.07
    NSS
    0.07
    Times
    0.07
    .times
    0.06
    Workspace
    0.06
     Times
    0.06
    tps
    0.06
     synd
    0.06
     unto
    0.06
    Gem
    0.06
    Activations Density 0.005%

    No Known Activations