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. 19-RESID-POST-AA
    6. 51336
    Prev
    Next
    INDEX
    Explanations

    speaking

    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
    Picker
    -0.07
    anth
    -0.06
     Ihr
    -0.06
     MF
    -0.06
    =tk
    -0.06
    .tableView
    -0.06
    Modify
    -0.06
    ,"
    -0.06
    ,”
    -0.05
     Stake
    -0.05
    POSITIVE LOGITS
     حم
    0.08
     SAMPLE
    0.07
    .sheet
    0.07
     consultation
    0.07
    _blk
    0.07
     учнів
    0.07
    oralType
    0.07
     energies
    0.06
     disillusion
    0.06
    .ps
    0.06
    Activations Density 0.009%

    No Known Activations