© 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. 89126
    Prev
    Next
    INDEX
    Explanations

    medical complications

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens marking the start of a “Complications” section or heading describing adverse outcomes.

    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
     pH
    -0.08
    herence
    -0.06
     النس
    -0.06
     Energy
    -0.06
     đăng
    -0.06
    _o
    -0.06
     pense
    -0.06
     nas
    -0.06
     aerobic
    -0.06
    —as
    -0.06
    POSITIVE LOGITS
     complications
    0.12
     complication
    0.09
     complicated
    0.09
    лл
    0.07
    pecial
    0.07
    टक
    0.07
     scandal
    0.07
    itler
    0.07
     civilized
    0.06
    :mm
    0.06
    Activations Density 0.007%

    No Known Activations