© 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. 22-LLAMASCOPE-RES-131K
    6. 4223
    Prev
    Next
    INDEX
    Explanations

    the word "Gent" 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
    ITY
    -0.08
    yers
    -0.07
    SELL
    -0.07
    arding
    -0.07
    trak
    -0.07
    ÄŁan
    -0.07
    CTION
    -0.07
    iedades
    -0.07
    oÄŁ
    -0.06
    eries
    -0.06
    POSITIVE LOGITS
    lemen
    0.13
     Gent
    0.08
    lem
    0.08
     gent
    0.08
    ertainment
    0.07
    LEM
    0.07
    gent
    0.07
    ucky
    0.07
    leness
    0.07
    ile
    0.07
    Activations Density 0.002%

    No Known Activations