© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 53682
    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_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
    ucas
    -0.07
    prak
    -0.07
    endl
    -0.06
     ве
    -0.06
     Wi
    -0.06
     fiction
    -0.06
     näch
    -0.06
    .index
    -0.06
     quick
    -0.06
     convey
    -0.06
    POSITIVE LOGITS
    #
    0.08
    сім
    0.07
     Sultan
    0.07
    #__
    0.07
    fab
    0.06
    (constants
    0.06
     باشگاه
    0.06
     +#
    0.06
     Instruments
    0.06
    'nde
    0.06
    Activations Density 0.004%

    No Known Activations