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. 50752
    Prev
    Next
    INDEX
    Explanations

    HTML/code documents

    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
    AINS
    -0.07
     Ling
    -0.06
    _recursive
    -0.06
    річ
    -0.06
    ทย
    -0.06
     thighs
    -0.06
     readOnly
    -0.06
     derail
    -0.06
     erection
    -0.06
    ใคร
    -0.06
    POSITIVE LOGITS
     Sa
    0.08
     noticed
    0.07
    APTER
    0.07
    Utf
    0.07
    apus
    0.07
     اقتصاد
    0.06
    AU
    0.06
     UserName
    0.06
     Symposium
    0.06
    عب
    0.06
    Activations Density 0.011%

    No Known Activations