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. 43909
    Prev
    Next
    INDEX
    Explanations

    mentions of location-specific phrases or entities

    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
    InterfaceOrientation
    -0.07
     kraje
    -0.07
    unga
    -0.07
     Areas
    -0.07
     Walls
    -0.06
     centres
    -0.06
     jails
    -0.06
    phinx
    -0.06
     Locations
    -0.06
    env
    -0.06
    POSITIVE LOGITS
     street
    0.14
     way
    0.11
     road
    0.10
     block
    0.10
    eway
    0.09
    street
    0.09
     cul
    0.09
     tracks
    0.08
     interstate
    0.08
    reet
    0.08
    Activations Density 0.020%

    No Known Activations