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. 19-RESID-POST-AA
    6. 111707
    Prev
    Next
    INDEX
    Explanations

    controllers

    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
     Preconditions
    -0.07
    HttpResponse
    -0.06
     RegexOptions
    -0.06
    �
    -0.06
    Enumer
    -0.06
     southeastern
    -0.06
     i
    -0.06
     Κυ
    -0.06
     Assert
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     NTN
    0.07
    -cluster
    0.07
    inizin
    0.06
    uet
    0.06
     العراق
    0.06
    ालक
    0.06
    Volt
    0.06
    _dark
    0.06
    té
    0.06
     interesting
    0.06
    Activations Density 0.053%

    No Known Activations