© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 789
    Prev
    Next
    INDEX
    Explanations

    protective

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of a treatment’s protective or attenuating effects (e.g. “protective,” “attenuate,” “effect,” “inhibit”) in biomedical study text.

    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
    GUID
    -0.07
    subject
    -0.06
     Feedback
    -0.06
     nullable
    -0.06
     cascade
    -0.05
     organis
    -0.05
     undermine
    -0.05
     adress
    -0.05
    ANTLR
    -0.05
    cascade
    -0.05
    POSITIVE LOGITS
    UIView
    0.07
     เมตร
    0.07
    (Vertex
    0.07
     elbows
    0.07
    _executor
    0.06
     ninguna
    0.06
     lab
    0.06
     그의
    0.06
     warns
    0.06
     ihtiy
    0.06
    Activations Density 0.011%

    No Known Activations