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. 15-RESID-POST-AA
    6. 114770
    Prev
    Next
    INDEX
    Explanations

    code

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fu
    -0.07
    ış
    -0.06
     �
    -0.06
    (jsonPath
    -0.06
    [ip
    -0.06
    ersive
    -0.06
     장
    -0.06
    nar
    -0.06
    των
    -0.06
    mış
    -0.06
    POSITIVE LOGITS
     unfairly
    0.07
    Develop
    0.07
    #echo
    0.06
     graphite
    0.06
     Golden
    0.06
    otas
    0.06
     pact
    0.06
    :length
    0.06
     RGBA
    0.06
     unstable
    0.06
    Activations Density 0.035%

    No Known Activations