Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93108
    Prev
    Next
    INDEX
    Explanations

    management treatment

    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
    ==(
    -0.07
     treasurer
    -0.07
     düşman
    -0.06
    olum
    -0.06
     sexist
    -0.06
     Worce
    -0.06
     interpolated
    -0.06
     baseman
    -0.06
     cuck
    -0.06
    esion
    -0.06
    POSITIVE LOGITS
     Scalars
    0.07
    Radians
    0.07
    ره
    0.07
     evalu
    0.07
    AccessorType
    0.06
     autoc
    0.06
    rava
    0.06
    ipa
    0.06
     Aer
    0.06
    AffineTransform
    0.06
    Activations Density 0.021%

    No Known Activations