© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65954
    Prev
    Next
    INDEX
    Explanations

    .com

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -se
    -0.07
     TString
    -0.07
     patient
    -0.07
     lines
    -0.07
     stimulated
    -0.07
     messages
    -0.07
    -lines
    -0.06
    efa
    -0.06
    align
    -0.06
    -line
    -0.06
    POSITIVE LOGITS
     baker
    0.07
     calend
    0.06
    едера
    0.06
     tedav
    0.06
     своими
    0.06
    175
    0.06
    =http
    0.06
     údaje
    0.06
     motorcycles
    0.06
    Scala
    0.06
    Activations Density 0.005%

    No Known Activations