© 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. 19-RESID-POST-AA
    11. 53838
    Prev
    Next
    INDEX
    Explanations

    Numbers in the 700s

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Intent
    -0.07
    -case
    -0.07
     institute
    -0.07
    Array
    -0.07
    embrance
    -0.07
    ивают
    -0.07
     colour
    -0.06
    .place
    -0.06
    ��드
    -0.06
     расстоя
    -0.06
    POSITIVE LOGITS
    753
    0.07
    783
    0.07
    VO
    0.07
    	es
    0.07
    750
    0.07
    HE
    0.07
    повід
    0.06
    vu
    0.06
     preco
    0.06
     sqlCommand
    0.06
    Activations Density 0.054%

    No Known Activations