© 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. 5-LLAMASCOPE-RES-131K
    11. 126896
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "charged with" followed by a crime or offense

    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
    ality
    -0.09
    etus
    -0.07
    umo
    -0.07
    bero
    -0.07
    ally
    -0.07
    umar
    -0.07
    Rent
    -0.06
    ÑĢоб
    -0.06
    844
    -0.06
    resa
    -0.06
    POSITIVE LOGITS
    eyi
    0.07
    piar
    0.06
     Rubio
    0.06
    Defaults
    0.06
     Peggy
    0.06
    Jvm
    0.06
    aurus
    0.06
    pix
    0.06
    PPER
    0.06
     Ib
    0.05
    Activations Density 0.003%

    No Known Activations