© 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. 128610
    Prev
    Next
    INDEX
    Explanations

    requirements for travel authorization and documentation

    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
    rek
    -0.07
    ippy
    -0.07
    enk
    -0.07
    ãĥ³ãĥĸ
    -0.06
    ustom
    -0.06
    atcher
    -0.06
    atori
    -0.06
     anatomy
    -0.06
     sucker
    -0.06
    lech
    -0.06
    POSITIVE LOGITS
     Leban
    0.07
    PIO
    0.06
    è±
    0.06
     Bears
    0.06
     bear
    0.06
    èģ²
    0.06
    æ³ī
    0.06
    TypeID
    0.06
     English
    0.06
     originals
    0.06
    Activations Density 0.012%

    No Known Activations