© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125268
    Prev
    Next
    INDEX
    Explanations

    galaxies and scientific abstracts

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on astronomical object designations—especially galaxy catalog identifiers like “M 33,” “NGC 5457,” “M 101,” etc.—so it’s recognizing references to named galaxies.

    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
     Kar
    -0.06
    ystate
    -0.06
     süreci
    -0.06
    bdd
    -0.06
    .Helper
    -0.06
     Bal
    -0.06
    -friendly
    -0.06
    .Build
    -0.06
     pimp
    -0.06
    hide
    -0.06
    POSITIVE LOGITS
    ğan
    0.07
    ANTS
    0.06
     healthier
    0.06
     NSF
    0.06
     Problems
    0.06
    shapes
    0.06
    KW
    0.06
     Attributes
    0.06
     sey
    0.06
     cứu
    0.06
    Activations Density 0.005%

    No Known Activations