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. 43907
    Prev
    Next
    INDEX
    Explanations

    references to the word "lunatic" and its variations

    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
    NSNotification
    -0.06
    eec
    -0.06
    hores
    -0.06
    qml
    -0.06
    eut
    -0.06
    eel
    -0.06
    ë§ī
    -0.06
    _framework
    -0.06
    lez
    -0.05
    sms
    -0.05
    POSITIVE LOGITS
    atic
    0.18
    cheon
    0.17
    acy
    0.16
    atics
    0.15
    acies
    0.12
    enburg
    0.12
    ATIC
    0.12
    atik
    0.11
    ACY
    0.11
    ettes
    0.11
    Activations Density 0.002%

    No Known Activations