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. 22-LLAMASCOPE-RES-131K
    6. 5455
    Prev
    Next
    INDEX
    Explanations

    specific acronyms or proper nouns

    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
    leta
    -0.08
    ixa
    -0.08
    å¨ĺ
    -0.07
    CJK
    -0.07
    agens
    -0.07
    Ø´ÙħاÙĦÛĮ
    -0.07
    à¹īาย
    -0.07
    vanished
    -0.07
    ikan
    -0.07
    äm
    -0.06
    POSITIVE LOGITS
     Rocky
    0.10
    dy
    0.06
    s
    0.06
     rocky
    0.06
    ood
    0.06
    kin
    0.06
    hest
    0.06
    zza
    0.06
    ll
    0.05
    icious
    0.05
    Activations Density 0.001%

    No Known Activations