© 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. 92006
    Prev
    Next
    INDEX
    Explanations

    dehydration

    np_max-act · gemini-2.0-flash

    The neuron activates on words and word parts referring to drying or removal of moisture (e.g. “desiccation,” “dry,” “dried,” “drying”).

    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
     toy
    -0.07
     Playback
    -0.06
    PropertyValue
    -0.06
    ETY
    -0.06
     fis
    -0.06
     increment
    -0.06
     collision
    -0.06
     prisoners
    -0.06
    50
    -0.06
    ".$_
    -0.06
    POSITIVE LOGITS
    场
    0.07
    itulo
    0.06
    	model
    0.06
     Chennai
    0.06
    Elim
    0.06
     patriot
    0.06
    家族
    0.06
    Fraction
    0.06
     til
    0.06
     Chapters
    0.06
    Activations Density 0.020%

    No Known Activations