© 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. 15-LLAMASCOPE-RES-131K
    11. 27263
    Prev
    Next
    INDEX
    Explanations

    documents that reference agreements or templates related to shared responsibilities

    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
    èĶµ
    -0.08
    ẩy
    -0.07
    ä»ĭ
    -0.06
    desk
    -0.06
    yas
    -0.06
    ASSES
    -0.06
     ká»ĥ
    -0.06
    urf
    -0.06
    atan
    -0.06
    <*
    -0.06
    POSITIVE LOGITS
     legal
    0.08
     Legal
    0.07
    legal
    0.06
    pedia
    0.06
    UCT
    0.06
     legally
    0.06
    _filled
    0.06
    kyt
    0.06
    zte
    0.06
    ordova
    0.06
    Activations Density 0.001%

    No Known Activations