© 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 EvalsExportsAPI 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. 77266
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific nouns and their attributes related to individuals, actions, and circumstances in criminal news stories

    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
    asser
    -0.07
    bine
    -0.07
    Formatter
    -0.07
    OfString
    -0.07
    ãĥ³ãĥĢ
    -0.07
    erk
    -0.07
    stype
    -0.07
    utes
    -0.07
    ÑĥлÑĮÑĤа
    -0.07
    elere
    -0.07
    POSITIVE LOGITS
     man
    0.07
     woman
    0.07
    echan
    0.06
     someone
    0.06
     male
    0.06
     young
    0.06
    ged
    0.06
    odka
    0.06
     ac
    0.05
     employee
    0.05
    Activations Density 0.013%

    No Known Activations