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. 28470
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ERGY
    -0.07
     Fotos
    -0.07
     imagination
    -0.07
     Hoy
    -0.07
    Die
    -0.07
    UUID
    -0.06
     hodnoty
    -0.06
    地域
    -0.06
    ueue
    -0.06
     Murdoch
    -0.06
    POSITIVE LOGITS
     реп
    0.06
     shell
    0.06
     xét
    0.06
    _rsp
    0.06
     исслед
    0.06
    �
    0.06
     т
    0.06
    _OID
    0.06
    (commit
    0.06
    (Locale
    0.06
    Activations Density 0.024%

    No Known Activations