© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 90865
    Prev
    Next
    INDEX
    Explanations

    attributes and formatting cues related to table layout in documents

    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
    .cloudflare
    -0.08
    enheim
    -0.08
    intree
    -0.07
    viso
    -0.07
    $MESS
    -0.07
    strup
    -0.07
    dpi
    -0.07
    éĻIJ
    -0.07
    <context
    -0.07
     Horny
    -0.07
    POSITIVE LOGITS
    Ïģη
    0.06
     Gross
    0.06
    orer
    0.06
    ulong
    0.06
     Main
    0.05
    stab
    0.05
    овÑĥ
    0.05
     Null
    0.05
    unned
    0.05
     Mandal
    0.05
    Activations Density 0.001%

    No Known Activations