© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 125138
    Prev
    Next
    INDEX
    Explanations

    code logic

    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
    umps
    -0.07
     sentenced
    -0.06
    費
    -0.06
    -head
    -0.06
    藍
    -0.06
    miss
    -0.06
     pan
    -0.06
     πολι
    -0.06
     cà
    -0.06
     سخن
    -0.06
    POSITIVE LOGITS
    icl
    0.08
    .FixedSingle
    0.07
    leting
    0.07
        
    0.07
     <<-
    0.06
     toch
    0.06
    →→
    0.06
     mail
    0.06
    　　
    0.06
    MAND
    0.06
    Activations Density 0.001%

    No Known Activations