© 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. 73812
    Prev
    Next
    INDEX
    Explanations

    geographical locations and 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
    reed
    -0.07
    олов
    -0.07
    abee
    -0.07
    CEE
    -0.07
    iado
    -0.07
     nhu
    -0.07
     RadioButton
    -0.06
    afia
    -0.06
    anela
    -0.06
     Mellon
    -0.06
    POSITIVE LOGITS
     administr
    0.07
     village
    0.06
     com
    0.06
     Singap
    0.06
    etting
    0.06
    arella
    0.06
     parcel
    0.06
    å·ŀå¸Ĥ
    0.06
    uning
    0.06
    onica
    0.05
    Activations Density 0.019%

    No Known Activations