© 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. 83126
    Prev
    Next
    INDEX
    Explanations

    terms related to community events and organizational activities

    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
    .erb
    -0.07
     Consulting
    -0.06
    ÑĢиг
    -0.06
    моÑģ
    -0.06
    Conversation
    -0.06
    ukkit
    -0.06
    fax
    -0.06
    EDA
    -0.06
     weekends
    -0.06
    consult
    -0.06
    POSITIVE LOGITS
     annual
    0.10
     Annual
    0.09
     party
    0.08
    Annual
    0.08
     retreat
    0.07
    annual
    0.07
     awards
    0.07
     corporate
    0.07
    party
    0.07
     employees
    0.07
    Activations Density 0.063%

    No Known Activations