© 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. 108026
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or specific dates and times

    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
    eldon
    -0.06
    oka
    -0.06
     bulk
    -0.06
     Shea
    -0.06
    cock
    -0.06
    äºĪ
    -0.06
     Bulk
    -0.06
    sembl
    -0.06
    474
    -0.06
     em
    -0.05
    POSITIVE LOGITS
    ços
    0.08
    ONTAL
    0.07
    asan
    0.07
    agher
    0.07
    ¦y
    0.07
    Ware
    0.06
    _reordered
    0.06
    anova
    0.06
    aes
    0.06
    ancel
    0.06
    Activations Density 0.008%

    No Known Activations