© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 112855
    Prev
    Next
    INDEX
    Explanations

    fre

    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
    aw
    -0.09
    ain
    -0.08
     Hasan
    -0.08
    ault
    -0.08
     Jain
    -0.07
    oid
    -0.07
    ahn
    -0.07
     Said
    -0.07
    オン
    -0.07
    az
    -0.07
    POSITIVE LOGITS
     Gre
    0.12
     Fre
    0.11
    Gre
    0.11
     Gro
    0.11
    Fre
    0.10
     tre
    0.10
     Tre
    0.09
     Flo
    0.09
     Bre
    0.09
     Fro
    0.09
    Activations Density 0.079%

    No Known Activations