© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 105654
    Prev
    Next
    INDEX
    Explanations

    references to animals and wildlife

    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
    važ
    -0.08
    indr
    -0.08
    gers
    -0.08
    infeld
    -0.08
    waters
    -0.08
    venir
    -0.08
    ibbon
    -0.08
    sheet
    -0.07
    mmo
    -0.07
    anto
    -0.07
    POSITIVE LOGITS
    /people
    0.12
    istic
    0.10
     kingdom
    0.08
    -rights
    0.08
    hood
    0.07
    ized
    0.07
     Kingdom
    0.06
     rights
    0.06
    itarian
    0.06
    brid
    0.06
    Activations Density 0.016%

    No Known Activations