© 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. 106065
    Prev
    Next
    INDEX
    Explanations

    geographic distances and locations

    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
    uzzi
    -0.07
    aes
    -0.07
     Walton
    -0.06
    =>"
    -0.06
    midt
    -0.06
    ium
    -0.06
     kent
    -0.06
    bourne
    -0.05
    720
    -0.05
    insky
    -0.05
    POSITIVE LOGITS
     distances
    0.08
     distance
    0.07
    rah
    0.07
    .scalablytyped
    0.07
    imestone
    0.07
    SystemService
    0.07
    stad
    0.06
     mileage
    0.06
    .distance
    0.06
     omas
    0.06
    Activations Density 0.005%

    No Known Activations