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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55997
    Prev
    Next
    INDEX
    Explanations

    phrases indicating geographical locations and related activities

    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
    bish
    -0.07
    ElementException
    -0.06
    oley
    -0.06
    idel
    -0.06
    etas
    -0.06
     à¤ī
    -0.06
    ingt
    -0.06
    à¥Īà¤ł
    -0.06
     Schwarz
    -0.06
     repeat
    -0.06
    POSITIVE LOGITS
    ediator
    0.07
     UK
    0.07
     colors
    0.07
     Tort
    0.07
     markets
    0.07
    uk
    0.07
    chs
    0.07
    iba
    0.06
    uku
    0.06
    jr
    0.06
    Activations Density 0.015%

    No Known Activations