© 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. 90724
    Prev
    Next
    INDEX
    Explanations

    javascript

    np_max-act · gemini-2.0-flash

    elements related to web development involving HTML forms for user input or interaction.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects floating‐point numeric literals (numbers with a decimal point) in the text.

    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
    Severity
    -0.07
    照
    -0.07
     growers
    -0.06
    cx
    -0.06
    },{"
    -0.06
    [`
    -0.06
    溫
    -0.06
    unfold
    -0.06
     موجب
    -0.06
    ^{
    -0.06
    POSITIVE LOGITS
    _ENSURE
    0.07
     Clothing
    0.07
    ovatel
    0.06
     SOCKET
    0.06
    een
    0.06
     diced
    0.06
     reven
    0.06
     Postal
    0.06
     데이터
    0.06
     đèn
    0.06
    Activations Density 0.005%

    No Known Activations