Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76483
    Prev
    Next
    INDEX
    Explanations

    date-related information

    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
    عÙĨ
    -0.07
     Colleg
    -0.07
    ESSAGES
    -0.07
    į°
    -0.07
    á»Ń
    -0.07
    .Dto
    -0.06
    zas
    -0.06
    ä»ķ
    -0.06
    ockets
    -0.06
    ستاÙĨ
    -0.06
    POSITIVE LOGITS
     museum
    0.09
     exhibit
    0.08
     Museum
    0.08
     visitors
    0.07
    ucher
    0.07
    .sponge
    0.07
     permanent
    0.07
     visitor
    0.07
     curator
    0.06
     exhibits
    0.06
    Activations Density 0.010%

    No Known Activations