© 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. 18308
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps related to events

    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
    erosis
    -0.07
    inqu
    -0.06
    ients
    -0.06
    iosis
    -0.06
    &C
    -0.06
    ibbon
    -0.05
    esson
    -0.05
    ertos
    -0.05
    .plugins
    -0.05
    iri
    -0.05
    POSITIVE LOGITS
     pylint
    0.08
    'gc
    0.07
    669
    0.07
    ç´
    0.07
    496
    0.07
     Anonymous
    0.06
    ¯ÃĤ
    0.06
     tslib
    0.06
     Platz
    0.06
    iyatı
    0.06
    Activations Density 0.006%

    No Known Activations