© 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. 9-LLAMASCOPE-RES-131K
    11. 96994
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly various quotation marks and periods

    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
    quia
    -0.06
     Levin
    -0.06
    uien
    -0.06
     Lam
    -0.06
    trap
    -0.05
    ched
    -0.05
    ham
    -0.05
     Nap
    -0.05
    ecs
    -0.05
    52
    -0.05
    POSITIVE LOGITS
     اÙĦتÙĤ
    0.08
    atur
    0.08
    áºŃt
    0.08
    /Dk
    0.08
    ippo
    0.08
    @nate
    0.07
    gabe
    0.07
    ÑģоÑĢ
    0.07
    æĻ´
    0.07
     SqlParameter
    0.07
    Activations Density 0.015%

    No Known Activations