© 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. 9-LLAMASCOPE-RES-131K
    11. 94584
    Prev
    Next
    INDEX
    Explanations

    locations or geographic names

    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
    æĹıèĩªæ²»
    -0.07
    deo
    -0.06
     æĺ
    -0.06
     Mayo
    -0.06
    handleRequest
    -0.06
    824
    -0.06
    odesk
    -0.05
    bias
    -0.05
    ,copy
    -0.05
    vido
    -0.05
    POSITIVE LOGITS
    OSP
    0.07
    iland
    0.07
    æĶ
    0.07
    geh
    0.07
    astro
    0.07
     Gren
    0.06
    uffman
    0.06
    onta
    0.06
    ĥn
    0.06
    uar
    0.06
    Activations Density 0.036%

    No Known Activations