Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 30363
    Prev
    Next
    INDEX
    Explanations

    References

    np_max-act · gemini-2.0-flash

    The neuron activates on in-text citation markers (bracketed references like [@r2]).

    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
    DESC
    -0.07
    Na
    -0.07
    器
    -0.07
     �
    -0.06
     embarrass
    -0.06
    �
    -0.06
     menace
    -0.06
    記
    -0.06
     sắp
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     aust
    0.07
    licate
    0.07
    [f
    0.07
     Milton
    0.06
     homicides
    0.06
    ー
    0.06
     Ricky
    0.06
    [curr
    0.06
    abetic
    0.06
    (Menu
    0.06
    Activations Density 0.020%

    No Known Activations