© 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. 43526
    Prev
    Next
    INDEX
    Explanations

    Corrupted text

    np_max-act · gemini-2.0-flash

    The neuron is triggered by LaTeX‐style citation and reference commands (e.g. “\cite,” “\ref,” “\url,” and their backslashes).

    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
     �
    -0.06
    		↵	↵
    -0.06
     autobi
    -0.06
     leurs
    -0.06
    ПО
    -0.06
    �
    -0.06
    工程
    -0.06
     trie
    -0.06
    グル
    -0.06
     coch
    -0.06
    POSITIVE LOGITS
    aney
    0.06
     dismay
    0.06
     investigates
    0.06
     screens
    0.06
     fans
    0.06
    -ticket
    0.06
    >${
    0.06
     پی
    0.06
    (directory
    0.06
     Termin
    0.06
    Activations Density 0.087%

    No Known Activations