Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5207
    Prev
    Next
    INDEX
    Explanations

    words that include variations of "bat."

    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
    .inflate
    -0.07
    .Filters
    -0.07
    adin
    -0.07
    lian
    -0.06
    çĭIJ
    -0.06
     Ú©ÙĪØª
    -0.06
    iland
    -0.06
    eldon
    -0.06
    hatt
    -0.06
    à¤īत
    -0.06
    POSITIVE LOGITS
    ross
    0.10
    ROSS
    0.09
    Ĥæķ°
    0.06
    oes
    0.06
    778
    0.06
    ros
    0.06
    ROS
    0.06
    idlo
    0.06
    -wing
    0.06
    azeera
    0.06
    Activations Density 0.001%

    No Known Activations