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

    Neuronpedia

    APICircuit 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. 11-RESID-POST-AA
    6. 81197
    Prev
    Next
    INDEX
    Explanations

    reversal

    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
     long
    -0.07
    Lost
    -0.06
     occup
    -0.06
     belts
    -0.06
     Joshua
    -0.06
     battle
    -0.06
    Sp
    -0.06
     sched
    -0.06
     Really
    -0.06
     ship
    -0.06
    POSITIVE LOGITS
    рек
    0.07
     druhou
    0.07
    قر
    0.06
     ENTRY
    0.06
    _tD
    0.06
    arked
    0.06
     SWITCH
    0.06
    ñana
    0.06
    面积
    0.06
    	templateUrl
    0.06
    Activations Density 0.008%

    No Known Activations