© 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. 83141
    Prev
    Next
    INDEX
    Explanations

    repetitions and comparisons of ideas or concepts

    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
    Ñĸб
    -0.06
    uet
    -0.06
    ÏģιÏĥ
    -0.06
     далÑĮ
    -0.06
    ìĭ¤
    -0.06
    inue
    -0.06
    lio
    -0.06
    olar
    -0.06
    une
    -0.06
     stamp
    -0.05
    POSITIVE LOGITS
     with
    0.07
     withString
    0.07
     situation
    0.07
     for
    0.07
     обÑģÑĤ
    0.07
     case
    0.07
    andscape
    0.07
    ilir
    0.07
     applies
    0.06
    ìļĶ
    0.06
    Activations Density 0.024%

    No Known Activations