© 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. 41175
    Prev
    Next
    INDEX
    Explanations

    references to adversarial or opposing forces

    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
    _nsec
    -0.07
    lov
    -0.07
    ally
    -0.07
    orig
    -0.07
    ifestyles
    -0.07
    asia
    -0.07
    azo
    -0.07
    gere
    -0.07
    cher
    -0.07
    enge
    -0.07
    POSITIVE LOGITS
    liness
    0.08
    ess
    0.07
    rous
    0.07
    ARRANT
    0.07
    /host
    0.07
    /op
    0.06
    ship
    0.06
     ship
    0.06
    hood
    0.06
     ships
    0.06
    Activations Density 0.009%

    No Known Activations