Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43780
    Prev
    Next
    INDEX
    Explanations

    discussions related to movie theater policies and audience responses

    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
    akte
    -0.08
    ÙİØ§
    -0.07
    enty
    -0.07
     Television
    -0.06
     appropriation
    -0.06
    èĬ¸
    -0.06
     television
    -0.06
    ãĥĨãĥ¬ãĥĵ
    -0.06
    auty
    -0.06
     تÙĦÙģ
    -0.06
    POSITIVE LOGITS
     IM
    0.11
     AMC
    0.11
     multip
    0.10
     concessions
    0.10
     theater
    0.10
     concession
    0.10
     recl
    0.10
     auditor
    0.10
     showing
    0.10
     XD
    0.10
    Activations Density 0.021%

    No Known Activations