© 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. 25620
    Prev
    Next
    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash

    The neuron fires on the C# assembly‐info header section—detecting the “//” comment lines and the “[assembly: …]” metadata attribute declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    attributes associated with assembly configuration in programming.

    oai_token-act-pair · gpt-4o-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
    BTN
    -0.06
    нений
    -0.06
    -frame
    -0.06
     Walker
    -0.06
    eddar
    -0.06
    ければ
    -0.05
    ング
    -0.05
    -duration
    -0.05
    έρα
    -0.05
     узн
    -0.05
    POSITIVE LOGITS
     Sı
    0.08
    컨
    0.07
     generalize
    0.07
    Juan
    0.07
     dej
    0.07
     Zen
    0.07
    iked
    0.07
     Returning
    0.06
    .Rect
    0.06
     circ
    0.06
    Activations Density 0.003%

    No Known Activations