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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 118415
    Prev
    Next
    INDEX
    Explanations

    its

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stitches
    -0.06
     Sv
    -0.06
    client
    -0.06
    ifth
    -0.06
    Incre
    -0.06
    кої
    -0.06
    deer
    -0.06
    -resistant
    -0.06
    stre
    -0.06
    tribution
    -0.06
    POSITIVE LOGITS
     armour
    0.07
     Occupation
    0.07
    考试
    0.06
     spectra
    0.06
    DateString
    0.06
     المتحدة
    0.06
    =#{
    0.06
     Yog
    0.06
     Maxim
    0.06
     методи
    0.06
    Activations Density 0.031%

    No Known Activations