© 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. 3-RESID-POST-AA
    11. 95919
    Prev
    Next
    INDEX
    Explanations

    [^

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     direction
    -0.07
    ]"
    -0.07
     اصلی
    -0.07
     ά
    -0.07
     as
    -0.06
     l
    -0.06
     pass
    -0.06
     reap
    -0.06
     prvním
    -0.06
     sands
    -0.06
    POSITIVE LOGITS
    [^
    0.30
    ([^
    0.12
    pageSize
    0.07
    (^
    0.06
    Assets
    0.06
    $fields
    0.06
    :key
    0.06
    (page
    0.06
    .Mock
    0.06
    tape
    0.06
    Activations Density 0.001%

    No Known Activations