© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 53248
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash

    The neuron detects the question word "How" (typically at the start of a question).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    оту
    -0.07
    ighbor
    -0.06
    Ger
    -0.06
    esion
    -0.06
    авис
    -0.06
    idente
    -0.06
    .Depth
    -0.06
    gien
    -0.06
    κος
    -0.06
     dyn
    -0.06
    POSITIVE LOGITS
     Alicia
    0.07
    rear
    0.06
    .Select
    0.06
    叫
    0.06
     abandoning
    0.06
    βολ
    0.06
     환
    0.06
     accommodation
    0.06
     consuming
    0.06
     medicinal
    0.06
    Activations Density 0.020%

    No Known Activations