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. 123469
    Prev
    Next
    INDEX
    Explanations

    scientific/medical research

    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
     gap
    -0.07
     strengthens
    -0.07
    ��
    -0.06
     Closet
    -0.06
     Noon
    -0.06
    	AND
    -0.06
     Gothic
    -0.06
    _rand
    -0.06
     отмеч
    -0.06
     boosted
    -0.06
    POSITIVE LOGITS
    .ag
    0.06
    忍
    0.06
     persone
    0.06
     embroidery
    0.06
     dahi
    0.06
     fake
    0.06
    UPLOAD
    0.06
    -rec
    0.06
    .Post
    0.06
    ちょっと
    0.06
    Activations Density 0.234%

    No Known Activations