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. 43691
    Prev
    Next
    INDEX
    Explanations

    technical symbols or notations used in mathematical contexts

    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
     shitty
    -0.08
     fucked
    -0.07
     ridiculous
    -0.07
     terrible
    -0.07
     fucking
    -0.07
     bullshit
    -0.07
     horrible
    -0.07
     terrifying
    -0.07
     misunderstanding
    -0.07
     unfortunate
    -0.07
    POSITIVE LOGITS
     Sen
    0.09
     Asheville
    0.08
     Henderson
    0.08
    Sen
    0.07
     Just
    0.07
     lately
    0.07
     sen
    0.07
     Bender
    0.07
     SEN
    0.07
    Christian
    0.07
    Activations Density 0.002%

    No Known Activations