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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 112091
    Prev
    Next
    INDEX
    Explanations

    Jackson

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drawable
    -0.06
    \Test
    -0.06
    دید
    -0.06
    véd
    -0.06
    رود
    -0.06
     persistence
    -0.06
    (Card
    -0.06
    یش
    -0.06
    ीश
    -0.05
    爷
    -0.05
    POSITIVE LOGITS
     professional
    0.07
     proficiency
    0.07
    。“
    0.07
    .Total
    0.06
    	inst
    0.06
    Months
    0.06
    .lu
    0.06
    545
    0.06
     лечения
    0.06
    Canon
    0.06
    Activations Density 0.003%

    No Known Activations