© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12809
    Prev
    Next
    INDEX
    Explanations

    congestion

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “congestão” (and its English equivalent “congestion”), i.e. it detects mentions of congestion.

    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
    4
    -0.08
     Stud
    -0.07
    lights
    -0.06
    2
    -0.06
     título
    -0.06
     Skywalker
    -0.06
    392
    -0.06
     Apprentice
    -0.06
    レビ
    -0.06
     birth
    -0.06
    POSITIVE LOGITS
     congestion
    0.13
     congest
    0.10
     congregation
    0.09
     congreg
    0.09
    -io
    0.08
    нен
    0.07
     Cong
    0.07
     conven
    0.07
    िग
    0.07
     commons
    0.07
    Activations Density 0.002%

    No Known Activations