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

    Neuronpedia

    Jacobian LensNEW
    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. 16432
    Prev
    Next
    INDEX
    Explanations

    instances of insults and derogatory language

    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
    orr
    -0.07
    ilden
    -0.07
    yles
    -0.07
    ales
    -0.07
    gie
    -0.07
    erness
    -0.07
    stral
    -0.07
    ills
    -0.07
    elp
    -0.07
    over
    -0.07
    POSITIVE LOGITS
    ively
    0.09
    ingly
    0.09
    ably
    0.08
    uous
    0.08
    atory
    0.08
    antly
    0.07
    ive
    0.07
    271
    0.07
    urb
    0.06
    acios
    0.06
    Activations Density 0.004%

    No Known Activations