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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 99914
    Prev
    Next
    INDEX
    Explanations

    choose

    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
    _smooth
    -0.07
    passed
    -0.06
     punching
    -0.06
     booty
    -0.06
    _stride
    -0.06
    thren
    -0.06
     setPassword
    -0.06
     EDGE
    -0.06
     Doors
    -0.05
    sku
    -0.05
    POSITIVE LOGITS
     автом
    0.08
     teachings
    0.07
    เ�
    0.07
     comply
    0.07
     पस
    0.07
    ΙΑ
    0.07
     ∈
    0.07
     apiUrl
    0.07
    に行
    0.07
    levels
    0.07
    Activations Density 0.016%

    No Known Activations