© 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. 26965
    Prev
    Next
    INDEX
    Explanations

    references to government entities and actions

    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
     proposition
    -0.07
     perpet
    -0.06
     propositions
    -0.06
    ç¼ĺ
    -0.06
    ipro
    -0.06
    airy
    -0.06
    odafone
    -0.05
     propag
    -0.05
    ught
    -0.05
     Prop
    -0.05
    POSITIVE LOGITS
    .gov
    0.09
    egov
    0.08
    .nih
    0.07
     Cabinet
    0.07
    akter
    0.07
     bil
    0.07
    odate
    0.07
    è®
    0.07
    UNK
    0.07
    -caption
    0.07
    Activations Density 0.083%

    No Known Activations