© 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. 15-LLAMASCOPE-RES-131K
    11. 87284
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a location or origin associated with organizations or entities

    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
    олÑĮно
    -0.07
    CREMENT
    -0.07
    CONS
    -0.07
     abs
    -0.07
    kening
    -0.07
    nap
    -0.07
    ifestyles
    -0.06
    .ie
    -0.06
    olesale
    -0.06
    uer
    -0.06
    POSITIVE LOGITS
    ye
    0.07
     Barton
    0.07
    lash
    0.06
     physically
    0.06
    uls
    0.06
    yar
    0.06
    oram
    0.06
    hq
    0.05
     United
    0.05
    YRO
    0.05
    Activations Density 0.005%

    No Known Activations