© 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 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. 33977
    Prev
    Next
    INDEX
    Explanations

    to/just

    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
    وف
    -0.07
    /key
    -0.07
     Keep
    -0.07
     fazer
    -0.07
    Keep
    -0.07
    _De
    -0.07
    aced
    -0.07
    _prop
    -0.06
     disse
    -0.06
    (N
    -0.06
    POSITIVE LOGITS
    CEEDED
    0.06
    '])↵
    0.06
    ("$.
    0.06
     irq
    0.06
    ]),↵
    0.06
     Predicate
    0.05
     scarc
    0.05
     plt
    0.05
    Maker
    0.05
     ciz
    0.05
    Activations Density 0.254%

    No Known Activations