© 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. 17-LLAMASCOPE-RES-131K
    11. 15885
    Prev
    Next
    INDEX
    Explanations

    punctuation characters that indicate dialogue and 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
    issen
    -0.08
    rok
    -0.07
     *}
    -0.07
    пÑĢимеÑĢ
    -0.07
    заб
    -0.07
    AVA
    -0.06
    commission
    -0.06
    éĹ®
    -0.06
    åķı
    -0.06
    vider
    -0.06
    POSITIVE LOGITS
    850
    0.07
    rous
    0.07
     observed
    0.06
    764
    0.06
    oire
    0.06
     notation
    0.06
    hari
    0.06
    notation
    0.06
    æĶ¿
    0.06
    Ĥæķ°
    0.06
    Activations Density 0.008%

    No Known Activations