© 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. 126062
    Prev
    Next
    INDEX
    Explanations

    media coverage

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs and phrases that frame or comment on media reporting—words like “describing,” “mentioning,” “reporting,” “focusing,” “breaking,” “downplayed,” and “vilified.”

    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
    steen
    -0.07
    Begin
    -0.07
     Ct
    -0.06
     Liberal
    -0.06
    .Hand
    -0.06
     Manila
    -0.06
    lfw
    -0.06
    /Data
    -0.06
     Cooperation
    -0.06
    iframe
    -0.06
    POSITIVE LOGITS
    为什么
    0.07
    athering
    0.06
    .Alignment
    0.06
    Attr
    0.06
    егра
    0.06
     trance
    0.06
     ソ
    0.06
     Tok
    0.06
     võ
    0.06
    ucz
    0.06
    Activations Density 0.030%

    No Known Activations