© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110321
    Prev
    Next
    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash

    The neuron detects references to genealogy and family‐history research (e.g. “family,” “genealogy,” “ancestors,” “tree,” “research”).

    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
     succeeds
    -0.07
    (start
    -0.06
     ************************************************************************
    -0.06
     उन
    -0.06
    tick
    -0.06
     cải
    -0.06
    Founder
    -0.06
    .Inner
    -0.06
    "One
    -0.05
     صد
    -0.05
    POSITIVE LOGITS
    Si
    0.07
    264
    0.06
     června
    0.06
     Module
    0.06
    险
    0.06
     intermitt
    0.06
    .email
    0.06
     physic
    0.06
    امی
    0.06
     grub
    0.06
    Activations Density 0.009%

    No Known Activations