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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28911
    Prev
    Next
    INDEX
    Explanations

    terms related to legal wrongdoing and misconduct

    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
    brick
    -0.08
    ÙĬراÙĨ
    -0.07
    kle
    -0.07
    ickle
    -0.07
    iren
    -0.07
    .scalablytyped
    -0.07
    oÅĻ
    -0.07
    CustomAttributes
    -0.07
    loff
    -0.07
    LEV
    -0.07
    POSITIVE LOGITS
    ities
    0.07
    fully
    0.06
     claim
    0.06
    ist
    0.06
     death
    0.06
    ists
    0.06
    idad
    0.06
     claims
    0.06
    URLRequest
    0.06
    idade
    0.06
    Activations Density 0.002%

    No Known Activations