© 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. 128861
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "text" in various forms

    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
    warts
    -0.07
    issing
    -0.07
    ibble
    -0.07
    aguay
    -0.06
    ueur
    -0.06
    hed
    -0.06
    abler
    -0.06
    lett
    -0.06
    anko
    -0.06
     dual
    -0.06
    POSITIVE LOGITS
    ual
    0.08
    icular
    0.08
    ually
    0.07
    ظ
    0.07
    ured
    0.07
    e
    0.07
    echn
    0.06
    ston
    0.06
    лÑİд
    0.06
    URED
    0.06
    Activations Density 0.015%

    No Known Activations