© 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. 27522
    Prev
    Next
    INDEX
    Explanations

    site

    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
    _complex
    -0.07
    ชาว
    -0.06
     предлож
    -0.06
     čt
    -0.06
    	buff
    -0.06
    Com
    -0.06
     wereld
    -0.06
    _cum
    -0.06
    Num
    -0.06
     creek
    -0.06
    POSITIVE LOGITS
     Location
    0.08
     location
    0.07
     hitter
    0.07
    τή
    0.07
    .Navigator
    0.07
    ----↵↵
    0.07
    -local
    0.06
          
    0.06
    िट
    0.06
    @Test
    0.06
    Activations Density 0.008%

    No Known Activations