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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 43480
    Prev
    Next
    INDEX
    Explanations

    specific identifiers related to geographical locations and events

    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
    ophil
    -0.06
    oplay
    -0.06
    á»ı
    -0.06
    olumn
    -0.06
    ifu
    -0.06
    tah
    -0.06
    achi
    -0.06
    .ColumnHeader
    -0.05
    ÅĤug
    -0.05
    år
    -0.05
    POSITIVE LOGITS
     false
    0.14
     Event
    0.13
     event
    0.13
    false
    0.12
     America
    0.12
     Organizer
    0.12
    Event
    0.11
    America
    0.11
     true
    0.11
     RSVP
    0.11
    Activations Density 0.008%

    No Known Activations