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. 7-RESID-POST-AA
    6. 93136
    Prev
    Next
    INDEX
    Explanations

    class

    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
    peace
    -0.07
    ickým
    -0.07
    ностей
    -0.07
     tốt
    -0.07
    _longitude
    -0.07
    Eat
    -0.06
    _colors
    -0.06
    FAILED
    -0.06
    /functions
    -0.06
    _masks
    -0.06
    POSITIVE LOGITS
     specify
    0.07
     motive
    0.07
     Essentially
    0.07
     specifying
    0.07
    Ѕ
    0.06
     Cli
    0.06
     preamble
    0.06
     inhal
    0.06
    /or
    0.06
     ไ
    0.06
    Activations Density 0.022%

    No Known Activations