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. 5634
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lack" and related terms indicating deficiency or absence

    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
    æĸ¹éĿ¢
    -0.06
     Connectivity
    -0.06
    usch
    -0.06
     Ellison
    -0.06
    ORA
    -0.06
     Ridley
    -0.06
     Nicola
    -0.06
    asia
    -0.06
    ook
    -0.06
     purposes
    -0.06
    POSITIVE LOGITS
     availability
    0.08
    availability
    0.07
     cumshot
    0.07
    HITE
    0.07
    för
    0.07
    wizard
    0.07
    WSC
    0.07
    ersonic
    0.07
    dash
    0.07
    edException
    0.07
    Activations Density 0.008%

    No Known Activations