© 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. 7-RESID-POST-AA
    11. 45569
    Prev
    Next
    INDEX
    Explanations

    (Method

    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
    ือง
    -0.07
     Balls
    -0.07
     instant
    -0.07
     tinh
    -0.06
     dál
    -0.06
     indication
    -0.06
     flashes
    -0.06
    ANTE
    -0.06
    нів
    -0.06
     tailor
    -0.06
    POSITIVE LOGITS
    (Method
    0.10
    marginLeft
    0.06
    emphasis
    0.06
     ČR
    0.06
    .Ret
    0.06
    Pol
    0.06
     perceive
    0.06
     COMM
    0.06
     。↵
    0.06
    loggedin
    0.06
    Activations Density 0.000%

    No Known Activations