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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 109804
    Prev
    Next
    INDEX
    Explanations

    �

    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
     certainty
    -0.07
    15
    -0.07
    -X
    -0.07
    -inter
    -0.07
     stored
    -0.07
     starving
    -0.07
     speaks
    -0.07
     internship
    -0.07
    -bit
    -0.07
    remember
    -0.07
    POSITIVE LOGITS
    (ID
    0.07
    CGFloat
    0.06
     FindObjectOfType
    0.06
    @Column
    0.06
    .conn
    0.06
    UILayout
    0.06
    웃
    0.06
     panc
    0.06
    ß
    0.06
    esses
    0.05
    Activations Density 0.060%

    No Known Activations