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. 43702
    Prev
    Next
    INDEX
    Explanations

    programming elements related to database transactions and payment processing

    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
    .azure
    -0.06
    zzo
    -0.06
    .
    -0.05
    .{
    -0.05
    *.
    -0.05
    :.
    -0.05
    adh
    -0.05
    ;
    -0.05
    Python
    -0.05
    ,{
    -0.05
    POSITIVE LOGITS
     unserialize
    0.13
     array
    0.12
     new
    0.11
     isset
    0.10
     clone
    0.10
     explode
    0.10
     @$_
    0.10
     parent
    0.09
    array
    0.09
     &$
    0.09
    Activations Density 0.021%

    No Known Activations