© 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. 81309
    Prev
    Next
    INDEX
    Explanations

    elements related to geographic mapping data

    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
     Middle
    -0.07
     m
    -0.07
     Vie
    -0.06
     M
    -0.06
    isman
    -0.06
     Gio
    -0.06
    é
    -0.06
    geb
    -0.06
     man
    -0.05
    /v
    -0.05
    POSITIVE LOGITS
    96
    0.10
    92
    0.09
    90
    0.09
    94
    0.09
    91
    0.08
    93
    0.08
    99
    0.08
    95
    0.08
    84
    0.07
    atto
    0.07
    Activations Density 0.052%

    No Known Activations