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. 15-RESID-POST-AA
    6. 114937
    Prev
    Next
    INDEX
    Explanations

    book

    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
    Baş
    -0.08
    eği
    -0.07
     vydání
    -0.06
    ために
    -0.06
    {name
    -0.06
     Dragon
    -0.06
    ************
    -0.06
    Dragon
    -0.06
    ιώ
    -0.06
     Idle
    -0.06
    POSITIVE LOGITS
    .View
    0.07
    лет
    0.07
    firebase
    0.06
     refurb
    0.06
     Stunden
    0.06
    \Admin
    0.06
     k�
    0.06
     decryption
    0.06
    jde
    0.06
     popover
    0.05
    Activations Density 0.000%

    No Known Activations