Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87503
    Prev
    Next
    INDEX
    Explanations

    references to political or ethical issues related to leadership and governance

    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
    201
    -0.14
    Û²Û°Û±
    -0.11
    usterity
    -0.11
     Zika
    -0.11
     Lyft
    -0.10
     âĢª
    -0.10
     systemd
    -0.10
     selfie
    -0.10
     emoji
    -0.09
     derp
    -0.09
    POSITIVE LOGITS
    200
    0.23
    Û²Û°Û°
    0.17
     Bush
    0.14
     iPod
    0.12
    Bush
    0.11
     Millennium
    0.10
     bush
    0.10
     DVD
    0.09
     ³³ ³³ ³³ ³³
    0.09
     Katrina
    0.09
    Activations Density 1.464%

    No Known Activations