© 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. 19-RESID-POST-AA
    6. 9397
    Prev
    Next
    INDEX
    Explanations

    one

    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
    arrass
    -0.07
    Look
    -0.07
     Xml
    -0.07
    spoken
    -0.07
    FragmentManager
    -0.06
     персп
    -0.06
    _hello
    -0.06
    ClassName
    -0.06
     Da
    -0.06
    (cid
    -0.06
    POSITIVE LOGITS
     لیگ
    0.07
     تومان
    0.06
    :r
    0.06
    磨
    0.06
     hl
    0.06
     fopen
    0.06
     equation
    0.06
    _rules
    0.06
     threw
    0.06
     Saunders
    0.06
    Activations Density 0.000%

    No Known Activations