© 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. 15-LLAMASCOPE-RES-131K
    11. 90332
    Prev
    Next
    INDEX
    Explanations

    phrases that assert the significance or necessity of understanding and addressing various conditions or situations

    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
     because
    -0.09
     поÑĤомÑĥ
    -0.09
     however
    -0.08
     porque
    -0.08
     therefore
    -0.07
     Because
    -0.07
    Because
    -0.07
    because
    -0.07
    empl
    -0.07
    egrator
    -0.07
    POSITIVE LOGITS
     jinak
    0.07
     otherwise
    0.07
    361
    0.07
     outr
    0.06
    quite
    0.06
    apon
    0.06
    uz
    0.06
    ãĥ¼ãĥ³
    0.06
    ãģ°
    0.06
    umas
    0.06
    Activations Density 0.132%

    No Known Activations