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

    Neuronpedia

    Jacobian LensNEW
    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. 57088
    Prev
    Next
    INDEX
    Explanations

    tr

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “fact” (as in “factually”) indicating an assessment of factual consistency.

    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
     구글상위
    -0.06
    ▍▍
    -0.06
    xbe
    -0.06
    .CENTER
    -0.06
     Sof
    -0.06
     PlayerPrefs
    -0.06
     chan
    -0.06
     veces
    -0.06
     DateTimeOffset
    -0.06
     Disclosure
    -0.06
    POSITIVE LOGITS
     commands
    0.06
    职
    0.06
    -town
    0.06
     получить
    0.06
     aided
    0.06
     플
    0.06
     invest
    0.06
     goodies
    0.06
     زیب
    0.06
    )">↵
    0.06
    Activations Density 0.001%

    No Known Activations