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. 15-RESID-POST-AA
    6. 114274
    Prev
    Next
    INDEX
    Explanations

    of

    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
     andere
    -0.06
     sect
    -0.06
     >>>
    -0.06
    �
    -0.06
     Secondly
    -0.06
    [url
    -0.06
     opts
    -0.06
     prices
    -0.06
    push
    -0.06
    You
    -0.06
    POSITIVE LOGITS
    ThreadPool
    0.07
    用品
    0.07
    -dist
    0.07
    filepath
    0.07
    jejer
    0.06
    acağ
    0.06
    στημα
    0.06
     уровень
    0.06
     iets
    0.06
     kullanımı
    0.06
    Activations Density 0.013%

    No Known Activations