© 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. 76387
    Prev
    Next
    INDEX
    Explanations

    mentions of appointments or elections to boards or official positions

    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
    /REC
    -0.08
    uling
    -0.07
    çīĻ
    -0.07
    ť
    -0.07
    vise
    -0.07
     attracts
    -0.06
    åIJĪæł¼
    -0.06
    udder
    -0.06
    igne
    -0.06
    enas
    -0.06
    POSITIVE LOGITS
     positions
    0.09
    .scalablytyped
    0.09
     position
    0.08
     Positions
    0.07
     rank
    0.07
    position
    0.07
     Position
    0.07
    ê´ij
    0.06
    appa
    0.06
     roles
    0.06
    Activations Density 0.011%

    No Known Activations