© 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. 61336
    Prev
    Next
    INDEX
    Explanations

    sentences expressing disbelief or critical questioning

    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
    lew
    -0.07
    optgroup
    -0.07
    roup
    -0.07
     rental
    -0.06
    ÑĥлÑĮ
    -0.06
    ops
    -0.06
    eniable
    -0.06
    олÑĮкÑĥ
    -0.06
    alendar
    -0.06
    undry
    -0.06
    POSITIVE LOGITS
    imli
    0.07
    ãģ£ãģı
    0.07
    hoa
    0.07
    _GU
    0.06
    abbo
    0.06
    éħį
    0.06
     conflicts
    0.06
    ajo
    0.06
    535
    0.06
    æĭħå½ĵ
    0.06
    Activations Density 0.036%

    No Known Activations