© 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. 128751
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens appearing in citation or reference contexts (e.g. author names, “by,” “using the results of,” and year‐ or bracketed‐citation markers).

    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
    Idx
    -0.07
     nickel
    -0.06
    .dgv
    -0.06
    Dic
    -0.06
     Wagner
    -0.06
    song
    -0.06
    robots
    -0.06
    Dlg
    -0.05
    dera
    -0.05
    participant
    -0.05
    POSITIVE LOGITS
     [+
    0.07
     م
    0.07
     Oasis
    0.06
    aid
    0.06
     �
    0.06
    haled
    0.06
     面
    0.06
    […
    0.06
     fyz
    0.06
     не
    0.06
    Activations Density 0.017%

    No Known Activations