© 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. 11-RESID-POST-AA
    11. 79196
    Prev
    Next
    INDEX
    Explanations

    best

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behavioral
    -0.07
    โล
    -0.06
    applicant
    -0.06
    Player
    -0.06
     Brick
    -0.06
     alternating
    -0.06
    _clr
    -0.06
    Pattern
    -0.06
    ulators
    -0.06
     flooded
    -0.06
    POSITIVE LOGITS
    ....
    0.07
    (enable
    0.07
    _RESERVED
    0.06
     destined
    0.06
    наслід
    0.06
    @Before
    0.06
    _factory
    0.06
    Regards
    0.06
    mav
    0.06
    atsu
    0.06
    Activations Density 0.002%

    No Known Activations