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. 7-RESID-POST-AA
    6. 85985
    Prev
    Next
    INDEX
    Explanations

    city/state/university abbreviations

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igth
    -0.06
    χής
    -0.06
    ounded
    -0.06
    -v
    -0.06
     vyžad
    -0.06
     REQUEST
    -0.06
    brands
    -0.06
    chs
    -0.06
    $post
    -0.06
    chn
    -0.06
    POSITIVE LOGITS
    로부터
    0.07
    			
    ↵			
    ↵
    0.07
     áo
    0.07
     Picasso
    0.07
     وع
    0.07
     skyline
    0.06
     گونه
    0.06
     defa
    0.06
     çalışma
    0.06
     تحص
    0.06
    Activations Density 0.014%

    No Known Activations