© 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. 118418
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions or organizations

    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
    yor
    -0.06
    ordan
    -0.06
    afone
    -0.06
     ún
    -0.06
    atre
    -0.06
    имеÑĢ
    -0.06
     Ñħими
    -0.06
    ekil
    -0.06
    af
    -0.06
    ses
    -0.06
    POSITIVE LOGITS
     Gale
    0.07
    294
    0.07
    684
    0.07
    467
    0.07
    SessionFactory
    0.07
    PressEvent
    0.07
    ignum
    0.06
    293
    0.06
    Spoiler
    0.06
    457
    0.06
    Activations Density 0.008%

    No Known Activations