© 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. 2229
    Prev
    Next
    INDEX
    Explanations

    instances of the word "featured" and references to publications and exhibitions

    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
    ç¸
    -0.08
    etik
    -0.07
    çĩ
    -0.06
    occo
    -0.06
    ÑĶв
    -0.06
     пеÑĢен
    -0.06
    ļĮ
    -0.06
    inker
    -0.06
    criptor
    -0.06
    ÅĻÃŃz
    -0.06
    POSITIVE LOGITS
     feature
    0.09
    features
    0.08
    feature
    0.07
    vecs
    0.07
     FEATURE
    0.07
    utr
    0.07
    (feature
    0.07
     featured
    0.07
    .Feature
    0.07
    featured
    0.07
    Activations Density 0.020%

    No Known Activations