© 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. 128569
    Prev
    Next
    INDEX
    Explanations

    references to social issues and community development initiatives

    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
    kul
    -0.08
    ambi
    -0.06
    кÑĥлÑĮ
    -0.06
    åľ°
    -0.06
    isky
    -0.06
    etyl
    -0.06
    ernes
    -0.06
    aval
    -0.06
    ulu
    -0.06
    688
    -0.05
    POSITIVE LOGITS
    _firestore
    0.08
    Latch
    0.07
    ugar
    0.07
    ë§Ŀ
    0.06
    ç´
    0.06
    IDER
    0.06
    bits
    0.06
    ToOne
    0.06
    ãĤ¿
    0.06
    ëĤĺëĿ¼
    0.06
    Activations Density 0.045%

    No Known Activations