© 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. 28224
    Prev
    Next
    INDEX
    Explanations

    city

    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
    _MAXIMUM
    -0.06
     châu
    -0.06
    低
    -0.06
    depending
    -0.06
     gem
    -0.06
     грн
    -0.06
     interrog
    -0.06
     Speaking
    -0.06
    ancybox
    -0.06
     ini
    -0.06
    POSITIVE LOGITS
    ality
    0.07
    ague
    0.07
    rapy
    0.06
      ̄
    0.06
    "):
    0.06
    렬
    0.06
    )(__
    0.06
    resden
    0.06
    로그
    0.06
    ۱
    0.06
    Activations Density 0.012%

    No Known Activations