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. 43580
    Prev
    Next
    INDEX
    Explanations

    references to specific games and their elements

    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
    OVE
    -0.07
    коÑĤ
    -0.07
    uste
    -0.07
    bable
    -0.07
    umi
    -0.07
    moz
    -0.06
    employment
    -0.06
    æĪ´
    -0.06
    оÑıÑĤ
    -0.06
    ReadStream
    -0.06
    POSITIVE LOGITS
     Magic
    0.15
     MT
    0.13
    Magic
    0.12
     cards
    0.12
     booster
    0.11
     Commander
    0.11
     MAGIC
    0.11
     card
    0.11
     mt
    0.10
     Wizards
    0.10
    Activations Density 0.007%

    No Known Activations