© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 93971
    Prev
    Next
    INDEX
    Explanations

    oe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConnectionFactory
    -0.07
    _batch
    -0.07
    aphael
    -0.07
     Zur
    -0.06
     Gujarat
    -0.06
    orrh
    -0.06
    者
    -0.06
    ExecutionContext
    -0.06
     gonna
    -0.06
     بات
    -0.06
    POSITIVE LOGITS
    sanitize
    0.08
     Hundreds
    0.07
     scientifically
    0.06
    /tiny
    0.06
     Wal
    0.06
     Style
    0.06
    ilename
    0.06
    	bg
    0.06
    -types
    0.06
    ographical
    0.06
    Activations Density 0.002%

    No Known Activations