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

    Neuronpedia

    Jacobian LensNEW
    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. 15-RESID-POST-AA
    11. 86405
    Prev
    Next
    INDEX
    Explanations

    of

    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
    commit
    -0.07
    の中
    -0.07
    Open
    -0.07
     Blow
    -0.07
    Thin
    -0.06
    	onChange
    -0.06
    "Why
    -0.06
    _null
    -0.06
     obedient
    -0.06
    /open
    -0.06
    POSITIVE LOGITS
     autof
    0.06
    ATURE
    0.06
    vements
    0.06
     sqlCommand
    0.06
     SPEC
    0.06
    .BooleanField
    0.06
     انجام
    0.06
    (ac
    0.06
    =g
    0.05
     Sms
    0.05
    Activations Density 0.023%

    No Known Activations