© 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. 81298
    Prev
    Next
    INDEX
    Explanations

    of

    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
    cond
    -0.07
    bie
    -0.06
    ens
    -0.06
    ॉस
    -0.06
     BEN
    -0.06
    comed
    -0.06
     Tul
    -0.06
    lobe
    -0.06
     pla
    -0.06
     Antique
    -0.06
    POSITIVE LOGITS
     APPLICATION
    0.06
     '/
    0.06
     Ipsum
    0.06
     [%
    0.06
    ifa
    0.06
    yii
    0.06
    �
    0.06
     về
    0.06
    總
    0.06
    tahun
    0.06
    Activations Density 0.029%

    No Known Activations