Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 60063
    Prev
    Next
    INDEX
    Explanations

    </

    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
    _ord
    -0.07
     �
    -0.06
    ворення
    -0.06
    spd
    -0.06
    нів
    -0.06
    ダイ
    -0.06
     IDX
    -0.06
    Mal
    -0.06
     Wis
    -0.06
     Bashar
    -0.06
    POSITIVE LOGITS
     hm
    0.07
    ethe
    0.07
     IRQ
    0.06
     distorted
    0.06
    .WRITE
    0.06
     withRouter
    0.06
     성공
    0.06
     migrant
    0.06
     Vaccine
    0.06
     RelayCommand
    0.06
    Activations Density 0.002%

    No Known Activations