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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 30222
    Prev
    Next
    INDEX
    Explanations

    Historical events and places

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hp
    -0.06
    	search
    -0.06
    탁
    -0.06
     blunt
    -0.06
     getPath
    -0.06
     А
    -0.06
     Hp
    -0.06
    drivers
    -0.06
    ]->
    -0.06
    trail
    -0.06
    POSITIVE LOGITS
     соответств
    0.07
    tener
    0.06
     simples
    0.06
     entert
    0.06
    эф
    0.06
     Concat
    0.06
     nem
    0.06
    _interval
    0.06
     THEY
    0.06
    [\
    0.06
    Activations Density 0.064%

    No Known Activations