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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9825
    Prev
    Next
    INDEX
    Explanations

    cute

    np_max-act · gemini-2.0-flash

    cute

    np_max-act · gemini-2.5-flashTriggered by @aardvarkkr
    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
    'L
    -0.07
     Stanley
    -0.07
     Appointment
    -0.07
     risky
    -0.06
    Wal
    -0.06
    (Label
    -0.06
    fluid
    -0.06
     fon
    -0.06
     analysed
    -0.06
    asses
    -0.06
    POSITIVE LOGITS
     cute
    0.09
     Cute
    0.08
     citas
    0.07
     tetas
    0.07
    ottom
    0.07
     desired
    0.07
    タ
    0.07
    (hwnd
    0.07
    出
    0.07
    忍
    0.07
    Activations Density 0.005%

    No Known Activations