© 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. 9-LLAMASCOPE-RES-131K
    11. 95520
    Prev
    Next
    INDEX
    Explanations

    references to marking or labeling processes

    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
    ruk
    -0.07
    ì£
    -0.06
    pci
    -0.06
    remen
    -0.06
    bag
    -0.06
    -schema
    -0.06
    lobs
    -0.06
    orners
    -0.06
    (stdin
    -0.06
    riel
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥį
    0.07
    ÄŁÃ¼
    0.06
    çŁ¢
    0.06
    REFERRED
    0.06
    ê°ģ
    0.06
    eya
    0.06
    uckles
    0.06
     Kinh
    0.06
    lesia
    0.06
     Hawth
    0.06
    Activations Density 0.008%

    No Known Activations