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. 129156
    Prev
    Next
    INDEX
    Explanations

    pets, grains, and nuts

    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
     opendir
    -0.07
    dfa
    -0.07
     Uri
    -0.06
    に出
    -0.06
    648
    -0.06
    459
    -0.06
    pio
    -0.06
    (re
    -0.06
    uddy
    -0.06
    .af
    -0.06
    POSITIVE LOGITS
    $content
    0.07
    RELATED
    0.07
    FIELDS
    0.06
    혁
    0.06
     إلا
    0.06
    :Boolean
    0.06
    /".$
    0.06
    Ě
    0.06
    ,便
    0.06
     стат
    0.06
    Activations Density 0.489%

    No Known Activations