© 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. 94358
    Prev
    Next
    INDEX
    Explanations

    attributes that describe the characteristics and qualities of various cities and places

    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
     pillar
    -0.07
     Polo
    -0.06
    amt
    -0.06
    олиÑĤ
    -0.06
    forth
    -0.06
    uD
    -0.06
    T
    -0.06
    lando
    -0.06
    rea
    -0.06
    inke
    -0.06
    POSITIVE LOGITS
     intoler
    0.07
    à¥ģब
    0.07
     culture
    0.06
    marsh
    0.06
    æĨ
    0.06
    radu
    0.06
    culture
    0.06
    afi
    0.06
    644
    0.06
    ัà¸įà¸į
    0.06
    Activations Density 0.021%

    No Known Activations