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. 9-LLAMASCOPE-RES-131K
    6. 96131
    Prev
    Next
    INDEX
    Explanations

    references to temptation and inability to resist

    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
    ads
    -0.07
    aday
    -0.06
    eron
    -0.06
    o
    -0.06
    addy
    -0.06
    ali
    -0.06
    pra
    -0.06
    urai
    -0.06
    awy
    -0.06
    id
    -0.06
    POSITIVE LOGITS
    ziej
    0.07
    ingly
    0.07
    ÙĬÙĨÙĬØ©
    0.07
     temptation
    0.07
     heels
    0.07
    rored
    0.07
    íĸ
    0.06
    AffineTransform
    0.06
    abelle
    0.06
    gle
    0.06
    Activations Density 0.002%

    No Known Activations