© 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. 3385
    Prev
    Next
    INDEX
    Explanations

    references to well-known individuals and organizations associated with various fields, particularly relating to health, safety, and the environment

    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
    erp
    -0.09
    eras
    -0.08
    rex
    -0.07
    opia
    -0.07
    alic
    -0.07
    rep
    -0.07
    opes
    -0.07
    elper
    -0.07
    utt
    -0.07
    verse
    -0.07
    POSITIVE LOGITS
    ocalypse
    0.07
    och
    0.07
     hone
    0.07
    ìŀIJ기
    0.06
     inund
    0.06
     Orr
    0.06
    еÑĨ
    0.06
    ocht
    0.06
    ooled
    0.06
    inder
    0.06
    Activations Density 0.101%

    No Known Activations