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. 43910
    Prev
    Next
    INDEX
    Explanations

    statements related to assertions and validations in programming

    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
     
    -0.14
     '
    -0.13
     ‘
    -0.10
     ('
    -0.10
     null
    -0.09
     _
    -0.09
     a
    -0.09
     this
    -0.09
     [
    -0.09
    OperationException
    -0.08
    POSITIVE LOGITS
    ([]
    0.15
    (nil
    0.13
    ((*
    0.13
    (strings
    0.12
    ((&
    0.12
    strings
    0.12
    (fmt
    0.12
    (&
    0.12
     strings
    0.11
    ([]*
    0.11
    Activations Density 0.013%

    No Known Activations