© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68263
    Prev
    Next
    INDEX
    Explanations

    genes

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric measurements and quantitative genomic details (e.g., genome lengths, base‐pair counts, and gene counts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rylic
    -0.07
     joven
    -0.06
     Teaching
    -0.06
    leaning
    -0.06
     buffering
    -0.06
     Planning
    -0.06
    Planning
    -0.06
     specifying
    -0.06
     teaching
    -0.06
     acrylic
    -0.06
    POSITIVE LOGITS
    ्तन
    0.07
     일을
    0.07
    оти
    0.07
    escort
    0.07
    	work
    0.07
    ται
    0.07
     HOWEVER
    0.06
    _udp
    0.06
     http
    0.06
    theon
    0.06
    Activations Density 0.004%

    No Known Activations