© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 749
    Prev
    Next
    INDEX
    Explanations

    antibody immune responses

    np_max-act · gemini-2.0-flash

    The neuron responds to immunology‐related terms, especially words denoting immune responses (e.g. antibody, immune, immunization, responses, IgG).

    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
    .Does
    -0.07
     Dillon
    -0.07
     invoices
    -0.06
    TJ
    -0.06
     CVS
    -0.06
    应当
    -0.06
     عليك
    -0.06
    ContentSize
    -0.06
    pected
    -0.06
     본
    -0.06
    POSITIVE LOGITS
     �
    0.06
     deline
    0.06
     ""){↵
    0.06
    ()=>{↵
    0.06
     letras
    0.06
    мини
    0.06
     CGContext
    0.06
    opaque
    0.06
     gcc
    0.06
     irr
    0.06
    Activations Density 0.010%

    No Known Activations