© 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. 56263
    Prev
    Next
    INDEX
    Explanations

    code symbols

    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
     Venezuel
    -0.07
    ugu
    -0.07
    HttpResponse
    -0.07
     складу
    -0.06
    (withId
    -0.06
    	swap
    -0.06
    yi
    -0.06
    :string
    -0.06
    donnees
    -0.06
    藝
    -0.06
    POSITIVE LOGITS
     Checking
    0.08
     Met
    0.07
     But
    0.07
     but
    0.06
    738
    0.06
    读
    0.06
     �
    0.06
    *Math
    0.06
     +
    0.06
    684
    0.06
    Activations Density 0.043%

    No Known Activations