© 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. 30034
    Prev
    Next
    INDEX
    Explanations

    stif

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on short runs of Latin‐alphabet letters (e.g. “ire,” “ev,” etc.) embedded in otherwise non-Latin text, i.e. it flags code-switched or mixed‐script segments.

    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
     finest
    -0.07
    TECT
    -0.06
    	de
    -0.06
     very
    -0.06
     impair
    -0.06
    Equal
    -0.06
    출
    -0.06
    Nonce
    -0.06
     blasted
    -0.06
     Trash
    -0.06
    POSITIVE LOGITS
     udál
    0.06
     deutschland
    0.06
     uart
    0.06
     uc
    0.06
     rail
    0.06
     Swipe
    0.06
     vegas
    0.06
    305
    0.06
     duel
    0.06
     bakeka
    0.06
    Activations Density 0.018%

    No Known Activations