© 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. 15-LLAMASCOPE-RES-131K
    11. 90249
    Prev
    Next
    INDEX
    Explanations

    legal references to environmental and food safety regulations

    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
    âĢ¦↵
    -0.06
    olk
    -0.06
    inker
    -0.06
    ierz
    -0.05
     Charg
    -0.05
     veto
    -0.05
    wyn
    -0.05
     Script
    -0.05
    umo
    -0.05
    orca
    -0.05
    POSITIVE LOGITS
    Violation
    0.10
    -gnu
    0.08
    eyed
    0.08
    è§Ħå®ļ
    0.08
     violations
    0.07
    UDGE
    0.07
     applic
    0.07
    ollower
    0.07
    .cf
    0.07
    ueur
    0.07
    Activations Density 0.107%

    No Known Activations