© 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. 59041
    Prev
    Next
    INDEX
    Explanations

    Code and software releases

    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
    $m
    -0.08
    (lo
    -0.07
    _List
    -0.07
    oggle
    -0.07
     Sphere
    -0.06
     هر
    -0.06
     radiator
    -0.06
     Stem
    -0.06
     Least
    -0.06
    matrix
    -0.06
    POSITIVE LOGITS
     желез
    0.07
    -animation
    0.07
    (Employee
    0.07
     cata
    0.06
    	process
    0.06
     Sanct
    0.06
    づ
    0.06
    _SANITIZE
    0.06
    -Muslim
    0.06
    alat
    0.06
    Activations Density 0.025%

    No Known Activations