© 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. 92531
    Prev
    Next
    INDEX
    Explanations

    tv

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases that convey urgent, conditional threats or deadlines (e.g. “if,” “will,” “within 24 hours”), i.e. time-bound ultimata.

    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
     sug
    -0.07
    	clear
    -0.07
     �
    -0.07
    YLE
    -0.06
    MER
    -0.06
    /pr
    -0.06
    特
    -0.06
     iron
    -0.06
     Sug
    -0.06
     Rubin
    -0.06
    POSITIVE LOGITS
    _DEC
    0.06
    :return
    0.06
    _Stream
    0.06
    _case
    0.06
    _roll
    0.06
    sson
    0.06
    _flashdata
    0.06
    =("
    0.06
    Peak
    0.06
    Product
    0.06
    Activations Density 0.203%

    No Known Activations