© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41843
    Prev
    Next
    INDEX
    Explanations

    references to census-related data and statistics

    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
    SSIP
    -0.07
    isoft
    -0.07
    issan
    -0.07
    ôi
    -0.07
    enuity
    -0.07
    еÑĢÑĪ
    -0.07
    alysis
    -0.07
    bish
    -0.07
    ẽ
    -0.07
    eller
    -0.07
    POSITIVE LOGITS
     Hod
    0.06
    ģm
    0.06
    irror
    0.06
     Hamm
    0.05
     WR
    0.05
    AGIC
    0.05
     Hum
    0.05
     diagnostic
    0.05
    ami
    0.05
     for
    0.05
    Activations Density 0.001%

    No Known Activations