© 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. 86630
    Prev
    Next
    INDEX
    Explanations

    ological

    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
     shedding
    -0.06
    contro
    -0.06
     legislation
    -0.06
     noct
    -0.06
     Arlington
    -0.06
     movies
    -0.06
    /bind
    -0.06
     speakers
    -0.06
     preserving
    -0.06
    _san
    -0.06
    POSITIVE LOGITS
    接受
    0.07
    istrate
    0.07
     Ignore
    0.06
     required
    0.06
     dbg
    0.06
    πος
    0.06
    charg
    0.06
    .Logger
    0.06
     },↵↵↵
    0.06
    .IsNotNull
    0.06
    Activations Density 0.001%

    No Known Activations