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. 43453
    Prev
    Next
    INDEX
    Explanations

    specific numeric and special character patterns or codes

    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
     private
    -0.08
    μÏĨ
    -0.07
    /private
    -0.07
    ÏģÏħ
    -0.07
     PRIVATE
    -0.06
    lassian
    -0.06
    uty
    -0.06
     Private
    -0.06
    .private
    -0.06
    _valor
    -0.06
    POSITIVE LOGITS
    change
    0.07
    if
    0.07
    before
    0.07
    	before
    0.07
    create
    0.07
    self
    0.06
    dro
    0.06
    unge
    0.06
    drop
    0.06
    end
    0.06
    Activations Density 0.004%

    No Known Activations