© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 35063
    Prev
    Next
    INDEX
    Explanations

    toxin exposure

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     udp
    -0.07
    руп
    -0.07
    cw
    -0.07
    Tail
    -0.06
     Asp
    -0.06
     Sav
    -0.06
    uf
    -0.06
     Required
    -0.06
    ̧
    -0.06
    4
    -0.06
    POSITIVE LOGITS
    猪
    0.06
    ,+
    0.06
     Zub
    0.06
     گردد
    0.06
     iCloud
    0.06
    佳
    0.06
    CO
    0.05
     UserController
    0.05
     externally
    0.05
    +-
    0.05
    Activations Density 0.035%

    No Known Activations