© 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. 7-RESID-POST-AA
    6. 60165
    Prev
    Next
    INDEX
    Explanations

    restriction

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scan
    -0.07
     crop
    -0.07
     فرود
    -0.06
     PAN
    -0.06
     fab
    -0.06
     Sweep
    -0.06
     manipulated
    -0.06
     گوشی
    -0.06
    işi
    -0.06
     logging
    -0.06
    POSITIVE LOGITS
     restriction
    0.07
     않았다
    0.06
     basın
    0.06
    <p
    0.06
    ordinates
    0.06
    options
    0.06
    .OneToOne
    0.06
     Я
    0.06
    URLOPT
    0.06
     ins
    0.06
    Activations Density 0.001%

    No Known Activations