© 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. 15-RESID-POST-AA
    11. 20517
    Prev
    Next
    INDEX
    Explanations

    Protection/Defense

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     memcmp
    -0.07
    locale
    -0.07
    Autowired
    -0.07
    udiant
    -0.07
    عکس
    -0.07
     serial
    -0.06
     Checked
    -0.06
    ít
    -0.06
    243
    -0.06
     앨
    -0.06
    POSITIVE LOGITS
     [|
    0.07
     lint
    0.06
                          ↵
    0.06
     abdomen
    0.06
     lor
    0.06
    ...,
    0.06
    Nickname
    0.06
    (;
    0.06
     (=
    0.06
    Pod
    0.06
    Activations Density 0.132%

    No Known Activations