© 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. 57582
    Prev
    Next
    INDEX
    Explanations

    themes related to collaboration and teamwork

    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
    illes
    -0.08
    opp
    -0.07
    isch
    -0.07
    à¸Ļà¸Ń
    -0.06
     Verfügung
    -0.06
    onder
    -0.06
     contre
    -0.06
    .bukkit
    -0.06
    ahlen
    -0.06
    elder
    -0.06
    POSITIVE LOGITS
     team
    0.10
     collective
    0.09
     everyone
    0.09
     multiple
    0.09
     teamwork
    0.09
     everybody
    0.08
    team
    0.08
    .team
    0.08
     Everyone
    0.08
    multiple
    0.08
    Activations Density 0.044%

    No Known Activations