© 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. 68872
    Prev
    Next
    INDEX
    Explanations

    medical studies

    np_max-act · gemini-2.0-flash

    The neuron fires on comparative result phrases in study reports—especially constructions like “Patients with … had higher … vs …” that present statistical contrasts.

    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
     brittle
    -0.07
    .TO
    -0.07
     Tah
    -0.07
     CBD
    -0.06
     Mouse
    -0.06
     yüz
    -0.06
     경
    -0.06
     withstand
    -0.06
    -figure
    -0.06
     Fiona
    -0.06
    POSITIVE LOGITS
    _dat
    0.06
     readFile
    0.06
     Να
    0.06
    reek
    0.06
    ,[],
    0.06
     adı
    0.06
    inicio
    0.06
    ############################
    0.06
     στρα
    0.06
    Loaded
    0.06
    Activations Density 0.058%

    No Known Activations