© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    6. 90721
    Prev
    Next
    INDEX
    Explanations

    Times, dates, sporting events

    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
    osit
    -0.07
    徽
    -0.06
    _cloud
    -0.06
    rectangle
    -0.06
     linewidth
    -0.06
    학
    -0.06
    estre
    -0.06
     cervical
    -0.06
    	callback
    -0.06
    .getInputStream
    -0.06
    POSITIVE LOGITS
     hairst
    0.06
    Scala
    0.06
     WithEvents
    0.06
     Updated
    0.06
     fel
    0.06
    PAR
    0.06
     TPM
    0.06
     android
    0.06
    (KeyCode
    0.06
     GK
    0.06
    Activations Density 0.116%

    No Known Activations