© 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. 2874
    Prev
    Next
    INDEX
    Explanations

    geographic locations and their historical significance

    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
    ango
    -0.07
     Hass
    -0.07
     dy
    -0.06
     tr
    -0.06
    studio
    -0.06
    owan
    -0.06
    ountain
    -0.06
     (
    -0.06
    ird
    -0.06
     dir
    -0.06
    POSITIVE LOGITS
    lish
    0.08
    VERR
    0.08
    ALER
    0.08
    KER
    0.08
    дап
    0.07
    /GPL
    0.07
    Detach
    0.07
    onn
    0.07
    å§Ĩ
    0.07
    isel
    0.07
    Activations Density 0.005%

    No Known Activations