© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93654
    Prev
    Next
    INDEX
    Explanations

    phrases indicating financial or betting-related contexts

    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
    iego
    -0.08
    thon
    -0.08
    LOCKS
    -0.07
    quat
    -0.07
    ottes
    -0.07
    ymb
    -0.07
    eur
    -0.07
    imbus
    -0.06
    icum
    -0.06
    aires
    -0.06
    POSITIVE LOGITS
    zel
    0.10
    ters
    0.10
    ting
    0.08
    365
    0.07
    tings
    0.07
    cher
    0.07
    anz
    0.07
    .Invariant
    0.07
    umen
    0.07
    ros
    0.07
    Activations Density 0.006%

    No Known Activations