© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91315
    Prev
    Next
    INDEX
    Explanations

    tumor

    np_max-act · gemini-2.0-flash

    The neuron activates on terms referring to tumor xenograft cancer models (e.g. tumor, xenograft, carcinoma, mice, human).

    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
    Checkpoint
    -0.08
    indexed
    -0.07
     ngay
    -0.07
    _transaksi
    -0.07
    Proveedor
    -0.07
     Calder
    -0.07
     isim
    -0.07
    isk
    -0.07
    cdf
    -0.06
     설정
    -0.06
    POSITIVE LOGITS
     impair
    0.07
    .Identity
    0.06
     >↵↵
    0.06
    thalm
    0.06
    (?:
    0.05
     //'
    0.05
     debtor
    0.05
    нять
    0.05
     alteration
    0.05
    nah
    0.05
    Activations Density 0.011%

    No Known Activations