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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3788
    Prev
    Next
    INDEX
    Explanations

    mentions of stakeholders and their involvement in various contexts

    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
    lernen
    -0.09
    lio
    -0.08
    ned
    -0.08
    Å©
    -0.08
    íģ¼
    -0.08
    tÄĽÅ¾
    -0.08
    nie
    -0.08
     Äijô
    -0.08
    TINGS
    -0.08
    zen
    -0.08
    POSITIVE LOGITS
    hip
    0.15
    hips
    0.12
    hood
    0.09
     who
    0.09
    hp
    0.08
     stake
    0.08
     groups
    0.08
     interested
    0.07
    holder
    0.07
    er
    0.07
    Activations Density 0.003%

    No Known Activations