© 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. 119457
    Prev
    Next
    INDEX
    Explanations

    locations and addresses related to businesses and venues

    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
     and
    -0.07
    stor
    -0.06
     Pearson
    -0.06
    ãĢĭçļĦ
    -0.06
    lr
    -0.06
    ades
    -0.06
    iel
    -0.06
    cko
    -0.06
    浦
    -0.06
    pek
    -0.05
    POSITIVE LOGITS
     Rd
    0.10
     Drive
    0.09
     Blvd
    0.09
     Road
    0.08
     bou
    0.08
    Drive
    0.08
     ave
    0.07
     Ave
    0.07
     Way
    0.07
    -drive
    0.07
    Activations Density 0.019%

    No Known Activations