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. 60084
    Prev
    Next
    INDEX
    Explanations

    typically

    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
    ,res
    -0.07
     blasting
    -0.07
     parametros
    -0.06
     Kosovo
    -0.06
    66
    -0.06
    IVES
    -0.06
     Раз
    -0.06
    888
    -0.06
     navbar
    -0.06
     lou
    -0.06
    POSITIVE LOGITS
     typically
    0.08
     typical
    0.08
     Turkish
    0.08
    TP
    0.08
    .Topic
    0.08
    typically
    0.08
    持
    0.07
     taxpayer
    0.07
    Mitch
    0.07
     matrimon
    0.07
    Activations Density 0.019%

    No Known Activations