© 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. 114344
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    954
    -0.07
     Jed
    -0.07
     dbs
    -0.07
    (argv
    -0.07
    904
    -0.07
     vieux
    -0.07
    parseInt
    -0.06
    iment
    -0.06
     října
    -0.06
    .findByIdAndUpdate
    -0.06
    POSITIVE LOGITS
    :create
    0.06
    _GENERIC
    0.06
     ninh
    0.06
     subclasses
    0.06
    )$/
    0.06
    Much
    0.06
    ricao
    0.06
     subclass
    0.06
    _blocks
    0.06
    牛
    0.06
    Activations Density 0.004%

    No Known Activations