Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5374
    Prev
    Next
    INDEX
    Explanations

    critical discussions surrounding global health and water access issues

    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
    CHandle
    -0.06
     Labrador
    -0.06
    iot
    -0.05
     Dexter
    -0.05
     NP
    -0.05
    STYPE
    -0.05
    CJK
    -0.05
    otre
    -0.05
    aches
    -0.05
     Personen
    -0.05
    POSITIVE LOGITS
     UN
    0.22
     World
    0.20
    UN
    0.20
    World
    0.17
     WHO
    0.17
    WHO
    0.15
     WORLD
    0.15
     UNESCO
    0.15
     UNU
    0.14
    .World
    0.14
    Activations Density 0.235%

    No Known Activations