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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96219
    Prev
    Next
    INDEX
    Explanations

    references to specific businesses or venues

    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
    +xml
    -0.08
    bourg
    -0.08
    plist
    -0.07
    _mD
    -0.07
    contres
    -0.07
    uelle
    -0.07
    andest
    -0.07
    OffsetTable
    -0.07
    .scalablytyped
    -0.07
    .LayoutParams
    -0.07
    POSITIVE LOGITS
    .SwingConstants
    0.06
     Mills
    0.06
     cons
    0.06
    owi
    0.05
    aky
    0.05
     neighborhood
    0.05
     celebrity
    0.05
     flavored
    0.05
    ullet
    0.05
    ONGL
    0.05
    Activations Density 0.013%

    No Known Activations