© 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. 12993
    Prev
    Next
    INDEX
    Explanations

    Cancer

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of the tumor microenvironment—especially the phrase “tumor microenvironment” and its key cellular components.

    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
     přist
    -0.07
    ili
    -0.07
    _responses
    -0.06
    edTextBox
    -0.06
     contribution
    -0.06
     Dirk
    -0.06
     freedoms
    -0.06
     обращ
    -0.06
     Warfare
    -0.06
     drones
    -0.06
    POSITIVE LOGITS
    jabi
    0.06
     Antoine
    0.06
    (QtCore
    0.06
    �
    0.06
     motivating
    0.06
    ])))
    0.06
    street
    0.06
    lovak
    0.06
    γων
    0.06
    	cin
    0.05
    Activations Density 0.012%

    No Known Activations