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. 7-RESID-POST-AA
    6. 10251
    Prev
    Next
    INDEX
    Explanations

    preferred

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ندگی
    -0.07
    iven
    -0.06
     �
    -0.06
    lüğü
    -0.06
    ्वय
    -0.06
     разви
    -0.06
    \Annotation
    -0.06
    ımıza
    -0.06
    gni
    -0.06
     cré
    -0.06
    POSITIVE LOGITS
     preferred
    0.08
     محمود
    0.07
     Side
    0.06
     trusted
    0.06
     reg
    0.06
     attacker
    0.06
    [file
    0.06
    ้ส
    0.06
     parish
    0.06
     activist
    0.06
    Activations Density 0.052%

    No Known Activations