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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127679
    Prev
    Next
    INDEX
    Explanations

    economic statistics related to vehicle sales and poverty levels

    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
    uset
    -0.08
    ands
    -0.07
    otime
    -0.06
    Ñĩи
    -0.06
    agal
    -0.06
    ãĤ±ãĥĥãĥĪ
    -0.06
    oker
    -0.06
    agli
    -0.06
    ÑİÑĢ
    -0.06
    اÙĦÙĩ
    -0.06
    POSITIVE LOGITS
    ADOW
    0.07
    elic
    0.06
    ackers
    0.06
    _formats
    0.06
     Hay
    0.06
     ROW
    0.06
     Casey
    0.06
    172
    0.06
     Crack
    0.06
    ka
    0.06
    Activations Density 0.010%

    No Known Activations