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. 80744
    Prev
    Next
    INDEX
    Explanations

    transfer

    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
    ahun
    -0.07
    ون
    -0.06
    buah
    -0.06
    Pont
    -0.06
    	    		
    -0.06
    Brown
    -0.06
     bile
    -0.06
    `ヽ
    -0.06
    ont
    -0.06
     sout
    -0.05
    POSITIVE LOGITS
     transfer
    0.17
     Transfer
    0.16
     transfers
    0.14
    Transfer
    0.13
     transferring
    0.12
    transfer
    0.12
     transferred
    0.11
    -transfer
    0.11
    fer
    0.11
    .transfer
    0.11
    Activations Density 0.016%

    No Known Activations