© 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 (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 59014
    Prev
    Next
    INDEX
    Explanations

    skin and body

    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
    fit
    -0.07
    InputStream
    -0.07
    d
    -0.07
    แข
    -0.07
     Closet
    -0.06
     gif
    -0.06
    ’hui
    -0.06
    she
    -0.06
     відбу
    -0.06
     canlı
    -0.06
    POSITIVE LOGITS
     }}"↵
    0.07
     dealloc
    0.06
    =");↵
    0.06
    *a
    0.06
    ……。
    0.06
    .IContainer
    0.06
    .setTime
    0.06
    ="?
    0.06
    }}"↵
    0.06
     доз
    0.06
    Activations Density 0.102%

    No Known Activations