© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127300
    Prev
    Next
    INDEX
    Explanations

    categories and demographics related to age and gender

    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
    ehler
    -0.07
    onz
    -0.07
    -keys
    -0.06
    agu
    -0.06
    arn
    -0.06
    vier
    -0.06
    atern
    -0.06
    783
    -0.06
    end
    -0.06
     SpringApplication
    -0.06
    POSITIVE LOGITS
     category
    0.10
    /category
    0.08
    category
    0.08
     Category
    0.08
    _category
    0.08
    -category
    0.08
    teg
    0.07
     class
    0.07
    .category
    0.07
     categoria
    0.07
    Activations Density 0.022%

    No Known Activations