© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 111724
    Prev
    Next
    INDEX
    Explanations

    Free offers and sign-ups

    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
    도로
    -0.07
     Mari
    -0.07
     Kia
    -0.07
     Io
    -0.07
    Mari
    -0.06
     brunette
    -0.06
     Springs
    -0.06
     Rank
    -0.06
    ząd
    -0.06
    anned
    -0.06
    POSITIVE LOGITS
    049
    0.07
    radient
    0.07
    ton
    0.06
     potatoes
    0.06
    母
    0.06
    (course
    0.06
    !',
    0.06
     learner
    0.06
     partnership
    0.06
     residual
    0.06
    Activations Density 0.000%

    No Known Activations