© 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. 9211
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    AxisSize
    -0.07
    Resolve
    -0.07
     Avengers
    -0.06
    .locations
    -0.06
     –↵↵
    -0.06
    species
    -0.06
     方法
    -0.06
     unsere
    -0.06
     blocks
    -0.06
    Finish
    -0.06
    POSITIVE LOGITS
    charge
    0.07
     thrilled
    0.06
     composers
    0.06
     INCIDENTAL
    0.06
     Cardinal
    0.06
    ALTH
    0.06
    řím
    0.06
     Nicolas
    0.06
     Pis
    0.06
     prat
    0.06
    Activations Density 0.028%

    No Known Activations