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. 43847
    Prev
    Next
    INDEX
    Explanations

    references to keys and their symbolic significance in relationships

    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
    ulur
    -0.07
    ropoda
    -0.06
    PIPE
    -0.06
    Äįen
    -0.06
    Ipv
    -0.06
    zano
    -0.06
    netinet
    -0.06
    itesse
    -0.06
    ä¸ĸç´Ģ
    -0.06
    anzi
    -0.05
    POSITIVE LOGITS
     keys
    0.15
     key
    0.13
     duplicates
    0.13
     duplicate
    0.12
     Keys
    0.11
    keys
    0.11
     duplication
    0.11
    -keys
    0.11
     copy
    0.11
     copies
    0.11
    Activations Density 0.007%

    No Known Activations