© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 22628
    Prev
    Next
    INDEX
    Explanations

    is

    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
     reasonable
    -0.08
     gor
    -0.07
    _Word
    -0.07
     Beng
    -0.07
    aga
    -0.07
     BYTE
    -0.06
     laz
    -0.06
    ila
    -0.06
    ken
    -0.06
    _ROOT
    -0.06
    POSITIVE LOGITS
    اون
    0.07
    (INT
    0.06
     protestors
    0.06
     PartialView
    0.06
    $tpl
    0.06
    BLUE
    0.06
     Include
    0.06
    
    0.06
     الات
    0.06
     소리
    0.06
    Activations Density 0.036%

    No Known Activations