© 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. 129158
    Prev
    Next
    INDEX
    Explanations

    mentions of open geographic data and community resources

    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
    reon
    -0.06
     vá»ĭ
    -0.06
    CCCCCC
    -0.06
    SCI
    -0.06
     Coca
    -0.06
    _SECURE
    -0.06
     Broadcast
    -0.06
    unden
    -0.06
     Sci
    -0.05
    uchen
    -0.05
    POSITIVE LOGITS
    oucher
    0.07
    wik
    0.07
     highway
    0.07
     Street
    0.07
     street
    0.07
    fi
    0.07
     streets
    0.07
     Donovan
    0.07
    /resource
    0.07
    erd
    0.06
    Activations Density 0.005%

    No Known Activations