© 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. 17-LLAMASCOPE-RES-131K
    11. 58653
    Prev
    Next
    INDEX
    Explanations

    occurrences of common punctuation marks

    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
    cratch
    -0.07
    zel
    -0.07
    ertools
    -0.06
    cÃŃm
    -0.06
    ODY
    -0.06
     chance
    -0.06
    chen
    -0.06
    .uc
    -0.06
    isko
    -0.06
    ubat
    -0.06
    POSITIVE LOGITS
     ÃĶ
    0.07
    edes
    0.07
    .viewport
    0.06
    ichten
    0.06
     FSM
    0.06
    èµ·ãģĵ
    0.06
    ìľ¡
    0.06
    egg
    0.06
    cpt
    0.06
    adv
    0.06
    Activations Density 0.001%

    No Known Activations