© 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. 87278
    Prev
    Next
    INDEX
    Explanations

    references to institutions and events related to government and public administration

    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
    ensis
    -0.08
    illac
    -0.06
    uky
    -0.06
    anity
    -0.06
    frei
    -0.06
    ption
    -0.06
    idel
    -0.06
     Blasio
    -0.06
    .firebaseapp
    -0.06
    -к
    -0.06
    POSITIVE LOGITS
    neath
    0.06
     [âĢ¦]↵↵
    0.06
    º
    0.06
    ãĥ¼ãĥł
    0.06
    OI
    0.06
    emento
    0.06
     Gallup
    0.06
    ürn
    0.06
    werk
    0.06
    laz
    0.06
    Activations Density 0.055%

    No Known Activations