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. 3-RESID-POST-AA
    6. 122765
    Prev
    Next
    INDEX
    Explanations

    dup/up

    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
     นาง
    -0.07
     Annotation
    -0.07
     �
    -0.06
    _para
    -0.06
    _ACTIONS
    -0.06
     Res
    -0.06
     vis
    -0.06
     irradi
    -0.06
    kám
    -0.06
     ATTRIBUTE
    -0.06
    POSITIVE LOGITS
     Dup
    0.22
     dup
    0.20
    dup
    0.19
    Dup
    0.18
     DUP
    0.16
    up
    0.13
    _dup
    0.12
    .dup
    0.12
    UP
    0.11
     duplex
    0.09
    Activations Density 0.002%

    No Known Activations