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. 22-LLAMASCOPE-RES-131K
    6. 5567
    Prev
    Next
    INDEX
    Explanations

    professional qualifications and experiences related to diving

    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
     gre
    -0.06
     occult
    -0.06
     dr
    -0.06
     lá»Ŀi
    -0.05
     patri
    -0.05
     mam
    -0.05
     elder
    -0.05
     gut
    -0.05
     Mah
    -0.05
     Coat
    -0.05
    POSITIVE LOGITS
     Instructor
    0.10
    EFR
    0.10
     dive
    0.10
     Dive
    0.09
     freed
    0.09
     dives
    0.09
     diving
    0.09
     bubbles
    0.09
    æ½ľ
    0.08
     gear
    0.08
    Activations Density 0.040%

    No Known Activations