© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56171
    Prev
    Next
    INDEX
    Explanations

    cell markers

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of cluster of differentiation (CD) cell‐surface markers (e.g., “CD38,” “CD56,” “CD127,” etc.).

    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
     Serv
    -0.08
    _math
    -0.07
    iers
    -0.06
     picked
    -0.06
    imum
    -0.06
     anomalies
    -0.06
     THROW
    -0.06
    _counter
    -0.06
     crucial
    -0.06
    ocene
    -0.06
    POSITIVE LOGITS
     getDate
    0.08
     Releases
    0.07
    ;margin
    0.07
    歳
    0.07
    езд
    0.07
    :"",↵
    0.07
    ılığ
    0.06
    .unlink
    0.06
     Dominion
    0.06
    miş
    0.06
    Activations Density 0.004%

    No Known Activations