© 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. 19-RESID-POST-AA
    6. 126764
    Prev
    Next
    INDEX
    Explanations

    Jacob

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thử
    -0.07
     RECE
    -0.07
    dyž
    -0.06
    #######↵
    -0.06
     У
    -0.06
     Ney
    -0.06
    唐
    -0.06
     Starr
    -0.06
     روز
    -0.06
     Tham
    -0.06
    POSITIVE LOGITS
     Jacob
    0.11
    Jacob
    0.10
    dig
    0.08
     Jacobs
    0.08
    act
    0.07
     acquired
    0.07
     Jake
    0.07
    aptor
    0.07
     IDisposable
    0.07
     negate
    0.07
    Activations Density 0.002%

    No Known Activations