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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92968
    Prev
    Next
    INDEX
    Explanations

    Free

    np_max-act · gemini-2.0-flash

    The neuron chiefly detects the word “free.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coding
    -0.07
     созд
    -0.06
     본
    -0.06
     burns
    -0.06
     drives
    -0.06
     understood
    -0.06
    reak
    -0.06
    рел
    -0.06
     shark
    -0.06
     exporting
    -0.06
    POSITIVE LOGITS
     Free
    0.08
     free
    0.08
    atas
    0.07
     Gaz
    0.07
    AuthGuard
    0.07
     무료
    0.07
    Gratis
    0.06
     Jerome
    0.06
     gratuito
    0.06
    amt
    0.06
    Activations Density 0.018%

    No Known Activations