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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 27-RESID-POST-AA
    6. 109893
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Multip
    -0.07
    'Re
    -0.07
    ||
    -0.07
     Norte
    -0.06
     Rein
    -0.06
     obtaining
    -0.06
     believer
    -0.06
     nowhere
    -0.06
    'T
    -0.06
     Utilities
    -0.06
    POSITIVE LOGITS
     Gors
    0.07
     enchant
    0.07
     AppBundle
    0.06
    ií
    0.06
     accusation
    0.06
    	check
    0.06
     nás
    0.06
     Bron
    0.06
    dater
    0.06
    Texto
    0.06
    Activations Density 0.052%

    No Known Activations