© 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. 3-RESID-POST-AA
    11. 121433
    Prev
    Next
    INDEX
    Explanations

    .observable

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NON
    -0.07
     Hell
    -0.06
    erece
    -0.06
     Equ
    -0.06
     через
    -0.06
    ervals
    -0.06
     Psychiatry
    -0.06
    -light
    -0.06
     tissues
    -0.06
     nop
    -0.06
    POSITIVE LOGITS
     deutsch
    0.09
     vamos
    0.09
    .Unmarshal
    0.08
    μένοι
    0.07
    enthal
    0.07
    .observable
    0.07
    achable
    0.07
    _IRQHandler
    0.07
    ulen
    0.07
     rude
    0.06
    Activations Density 0.012%

    No Known Activations