© 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. 40818
    Prev
    Next
    INDEX
    Explanations

    references to teamwork and the experiences of collaboration

    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
    azon
    -0.07
    eree
    -0.07
     ValueEventListener
    -0.07
    ̣
    -0.07
     FontStyle
    -0.07
    rsp
    -0.07
    UDGE
    -0.07
    emoc
    -0.07
    .imp
    -0.07
    ampie
    -0.07
    POSITIVE LOGITS
     team
    0.07
     colleagues
    0.07
     bunch
    0.06
     talented
    0.06
     my
    0.06
    col
    0.06
     such
    0.06
    æ±ī
    0.06
     staff
    0.05
     Tal
    0.05
    Activations Density 0.047%

    No Known Activations