© 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. 112011
    Prev
    Next
    INDEX
    Explanations

    sentiment analysis

    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
    压
    -0.07
     floors
    -0.07
     university
    -0.07
     sauces
    -0.07
     ensemble
    -0.06
    opleft
    -0.06
    	fun
    -0.06
     situ
    -0.06
    "]];↵
    -0.06
    ICY
    -0.06
    POSITIVE LOGITS
    weights
    0.07
      
    0.06
    manız
    0.06
     weights
    0.06
    setCellValue
    0.06
    療
    0.06
    ceptive
    0.06
     �
    0.06
    /run
    0.06
     BİR
    0.06
    Activations Density 0.007%

    No Known Activations