Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 20582
    Prev
    Next
    INDEX
    Explanations

    function

    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
    icus
    -0.06
    zzo
    -0.06
    MO
    -0.06
    _RAM
    -0.06
    乘
    -0.06
    zas
    -0.06
    (print
    -0.06
    SnackBar
    -0.06
    ецт
    -0.06
     Tak
    -0.06
    POSITIVE LOGITS
     dracon
    0.07
    罗斯
    0.06
    indy
    0.06
     disruptions
    0.06
    RATION
    0.06
    Going
    0.06
     gritty
    0.06
     cứu
    0.06
     initialise
    0.06
     erv
    0.06
    Activations Density 0.001%

    No Known Activations