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. 104304
    Prev
    Next
    INDEX
    Explanations

    negative

    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
     الداخ
    -0.07
    ού
    -0.06
    �
    -0.06
    -j
    -0.06
    pol
    -0.06
     boob
    -0.06
    Handled
    -0.06
     ifstream
    -0.06
    Basically
    -0.06
     финансов
    -0.06
    POSITIVE LOGITS
     illustrations
    0.08
     میزان
    0.07
    	
    0.07
     coarse
    0.07
     ayrıntılı
    0.06
     해외
    0.06
     pj
    0.06
     aplik
    0.06
    olu
    0.06
    Than
    0.06
    Activations Density 0.031%

    No Known Activations