© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 40624
    Prev
    Next
    INDEX
    Explanations

    question marks

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Driving
    -0.07
     préc
    -0.07
    課
    -0.07
     unh
    -0.06
    TURE
    -0.06
     Huang
    -0.06
     IDb
    -0.06
     treff
    -0.06
    >
    ↵
    ↵
    ↵
    -0.06
    Spark
    -0.06
    POSITIVE LOGITS
    ?
    0.07
     Jur
    0.06
     sites
    0.06
     ตาม
    0.06
     مات
    0.06
    act
    0.06
    >?
    0.06
    }?
    0.06
     equity
    0.06
    心里
    0.06
    Activations Density 0.004%

    No Known Activations