© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 53455
    Prev
    Next
    INDEX
    Explanations

    9

    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
    (ur
    -0.07
     withStyles
    -0.06
    爵
    -0.06
     glass
    -0.06
     histogram
    -0.06
     گردید
    -0.06
     radi
    -0.06
     veto
    -0.06
     deutschen
    -0.06
    _feed
    -0.06
    POSITIVE LOGITS
    (mat
    0.06
    .With
    0.06
    holder
    0.06
    (mid
    0.06
     セ
    0.06
    ARGET
    0.06
    ضان
    0.06
     MATCH
    0.06
    Tr
    0.06
     Disorder
    0.06
    Activations Density 0.011%

    No Known Activations