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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40328
    Prev
    Next
    INDEX
    Explanations

    symbols and characters from non-Latin scripts or encodings

    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
     æĬķ稿æĹ¥
    -0.07
    reira
    -0.07
    isto
    -0.07
    itch
    -0.07
    inho
    -0.06
    eyse
    -0.06
    rung
    -0.06
    Äĥm
    -0.06
    ÏĥÏĦά
    -0.06
    hic
    -0.06
    POSITIVE LOGITS
    ¾
    0.11
    ¿
    0.11
    ķ
    0.07
    µ
    0.07
    ught
    0.07
    imit
    0.07
    ·
    0.06
    ubber
    0.06
     acting
    0.06
     Acting
    0.06
    Activations Density 0.002%

    No Known Activations