© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 93983
    Prev
    Next
    INDEX
    Explanations

    especially

    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
    _inv
    -0.07
     ${(
    -0.07
     choke
    -0.07
     hoc
    -0.07
     calc
    -0.07
    -${
    -0.06
    戰
    -0.06
    .configure
    -0.06
     onboard
    -0.06
     allot
    -0.06
    POSITIVE LOGITS
    especially
    0.19
     especially
    0.12
    particularly
    0.09
     especialmente
    0.08
     Özellikle
    0.07
     veřej
    0.07
     především
    0.07
    尤
    0.07
     Especially
    0.07
    -President
    0.07
    Activations Density 0.015%

    No Known Activations