© 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. 5162
    Prev
    Next
    INDEX
    Explanations

    words related to dog breeds, specifically physical characteristics and attributes

    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
     Womens
    -0.07
    linger
    -0.07
    _sink
    -0.07
    jde
    -0.07
    alse
    -0.07
    lug
    -0.07
    (æľ¨
    -0.06
    usty
    -0.06
    /host
    -0.06
    aira
    -0.06
    POSITIVE LOGITS
     phen
    0.07
     inheritance
    0.07
     inherited
    0.07
     pattern
    0.07
     phenotype
    0.07
    andy
    0.07
     parti
    0.07
    lichkeit
    0.06
     genetic
    0.06
     genetics
    0.06
    Activations Density 0.013%

    No Known Activations