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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 54415
    Prev
    Next
    INDEX
    Explanations

    Technical/code/data

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oben
    -0.07
    _kv
    -0.06
    י�
    -0.06
    Trees
    -0.06
     sj
    -0.06
    онь
    -0.06
    aven
    -0.06
     показ
    -0.06
    elerinden
    -0.06
    wy
    -0.06
    POSITIVE LOGITS
     欧美
    0.07
     buggy
    0.06
    可能
    0.06
     percentile
    0.06
     recommends
    0.06
     Transactions
    0.06
    生物
    0.06
     lease
    0.06
     Νο
    0.06
    ankind
    0.06
    Activations Density 0.000%

    No Known Activations