© 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. 8866
    Prev
    Next
    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric version identifiers (e.g. “4.3.0,” “v5_8_1,” etc.), especially in @since or similar version-tag contexts.

    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
    Temperature
    -0.07
     bubbles
    -0.07
    _enter
    -0.07
     flow
    -0.07
     laid
    -0.07
    くる
    -0.07
    ikes
    -0.06
     Thornton
    -0.06
     Parade
    -0.06
    .Upload
    -0.06
    POSITIVE LOGITS
    ленні
    0.06
     heck
    0.06
     dakika
    0.06
     varsa
    0.06
    amment
    0.06
    �
    0.06
     ['-
    0.06
     станов
    0.06
    '+↵
    0.06
     abuses
    0.06
    Activations Density 0.002%

    No Known Activations