© 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. 125011
    Prev
    Next
    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash

    This neuron activates on the “x” used as a multiplication marker in dimensional measurements (e.g. “16 in. x 16 in.”).

    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
    #print
    -0.06
    _DST
    -0.06
    kur
    -0.06
     Iraq
    -0.06
    ervlet
    -0.06
    احة
    -0.06
     ISO
    -0.06
    ownership
    -0.06
     scanner
    -0.05
    世紀
    -0.05
    POSITIVE LOGITS
    nego
    0.07
     corresponds
    0.07
     Про
    0.06
     colorWithRed
    0.06
     dictated
    0.06
    Directed
    0.06
     Production
    0.06
     cubic
    0.06
     ihtiyac
    0.06
     requer
    0.06
    Activations Density 0.005%

    No Known Activations