© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91972
    Prev
    Next
    INDEX
    Explanations

    cd

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the acronym “QCD” (and closely related technical labels for Quantum Chromodynamics).

    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
    λ
    -0.07
    .leave
    -0.07
    beam
    -0.07
     μια
    -0.07
     Fro
    -0.06
    .one
    -0.06
     kterých
    -0.06
     USPS
    -0.06
     może
    -0.06
     Flask
    -0.06
    POSITIVE LOGITS
     cred
    0.06
    Did
    0.06
     شركة
    0.06
    ème
    0.06
     huh
    0.06
     cin
    0.06
    漫
    0.06
     swung
    0.06
     succes
    0.06
    Dim
    0.06
    Activations Density 0.001%

    No Known Activations