© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 121810
    Prev
    Next
    INDEX
    Explanations

    ing

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     altında
    -0.07
    _Anim
    -0.07
    iture
    -0.07
     Scan
    -0.06
     Mir
    -0.06
     Mods
    -0.06
    _extensions
    -0.06
    istrib
    -0.06
    ön
    -0.06
    UNC
    -0.06
    POSITIVE LOGITS
     neglected
    0.21
     neglect
    0.09
     употреб
    0.07
     Jake
    0.07
     ferment
    0.07
    administration
    0.06
    となる
    0.06
    دار
    0.06
     negligent
    0.06
     υπ
    0.06
    Activations Density 0.002%

    No Known Activations