© 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. 105903
    Prev
    Next
    INDEX
    Explanations

    disclaimers and limitations of liability

    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
    ếp
    -0.07
    quam
    -0.07
     Theatre
    -0.06
    åīĽ
    -0.06
    ournée
    -0.06
    ÑĢÑĥд
    -0.06
    inking
    -0.06
    ĵĺ
    -0.06
    212
    -0.06
    824
    -0.06
    POSITIVE LOGITS
     warrant
    0.08
     guarantee
    0.08
    isson
    0.07
    æł¸
    0.07
    uge
    0.07
    gua
    0.07
    anos
    0.07
    ittle
    0.06
     guarantees
    0.06
     Guar
    0.06
    Activations Density 0.004%

    No Known Activations