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. 44363
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "self" and variations of the word "this" in programming 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
     one
    -0.08
     T
    -0.07
    one
    -0.06
    :invoke
    -0.06
     null
    -0.06
    (Arrays
    -0.06
     new
    -0.06
    AndGet
    -0.06
     Jar
    -0.06
    ookies
    -0.06
    POSITIVE LOGITS
    .assertEqual
    0.11
    .assertIsInstance
    0.10
     isinstance
    0.09
    .assertIs
    0.08
    .assertIn
    0.08
    [self
    0.08
    (isinstance
    0.08
    -self
    0.08
    =self
    0.08
    (self
    0.07
    Activations Density 0.003%

    No Known Activations