© 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 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. 3562
    Prev
    Next
    INDEX
    Explanations

    specific locations and geographic regions

    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
    regor
    -0.07
     DeepCopy
    -0.07
    ervals
    -0.06
    idir
    -0.06
    bane
    -0.06
     WaitForSeconds
    -0.06
    sten
    -0.06
    uem
    -0.06
    isser
    -0.06
    \API
    -0.06
    POSITIVE LOGITS
    LATED
    0.07
    ennes
    0.07
    ige
    0.07
    .inst
    0.06
    yps
    0.06
    ROLS
    0.06
    peater
    0.06
    ymb
    0.06
    度
    0.06
    IENT
    0.06
    Activations Density 0.066%

    No Known Activations