© 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. 11-RESID-POST-AA
    11. 126796
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    The neuron activates on specification‐related terms in technical instructions—words that denote measurement ranges, appropriateness, compatibility, or expected values.

    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
    ystate
    -0.07
     monitoring
    -0.07
     FORWARD
    -0.07
    (Z
    -0.07
     login
    -0.07
     thrust
    -0.07
     Member
    -0.06
    checked
    -0.06
    GTK
    -0.06
     expired
    -0.06
    POSITIVE LOGITS
    بواسطة
    0.07
     chai
    0.07
     هایی
    0.07
     เล
    0.06
     dass
    0.06
     daß
    0.06
    ่าวว
    0.06
     komm
    0.06
    ">
↵
↵
    0.06
    ॉय
    0.06
    Activations Density 0.060%

    No Known Activations