© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 93978
    Prev
    Next
    INDEX
    Explanations

    data types

    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
     plush
    -0.06
     Mash
    -0.06
    	LOGGER
    -0.06
     quiet
    -0.06
    aleigh
    -0.06
    Money
    -0.06
     Miner
    -0.06
    ++];↵
    -0.06
    Detroit
    -0.06
     neurotrans
    -0.06
    POSITIVE LOGITS
     독
    0.07
    دة
    0.06
     �
    0.06
    _SEL
    0.06
    Δ
    0.06
     �
    0.06
    vue
    0.06
     adidas
    0.06
     XB
    0.06
     Jap
    0.06
    Activations Density 0.015%

    No Known Activations