© 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. 23-RESID-POST-AA
    6. 8029
    Prev
    Next
    INDEX
    Explanations

    ="

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vegan
    -0.07
    _column
    -0.07
     carousel
    -0.07
    (shift
    -0.06
    ifference
    -0.06
     Required
    -0.06
     Carousel
    -0.06
    Alternatively
    -0.06
     rr
    -0.06
     Pv
    -0.06
    POSITIVE LOGITS
    _FILENO
    0.06
    vince
    0.06
    fried
    0.06
     مس
    0.06
    الد
    0.06
    super
    0.06
    managed
    0.06
    ิทธ
    0.06
    ουμε
    0.06
    	End
    0.06
    Activations Density 0.004%

    No Known Activations