© 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. 126629
    Prev
    Next
    INDEX
    Explanations

    District

    np_max-act · gemini-2.0-flash

    legal terminology and references related to court orders or appeals.

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

    This neuron detects when a legal opinion header names a specific court district (e.g. “Fifth District of Texas at Dallas”).

    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
    046
    -0.07
    livě
    -0.07
    unteers
    -0.07
    -be
    -0.07
    .JPG
    -0.07
     Could
    -0.06
    ecektir
    -0.06
    ties
    -0.06
     다음과
    -0.06
     конферен
    -0.06
    POSITIVE LOGITS
     dorsal
    0.07
    HexString
    0.06
     diligent
    0.06
    -client
    0.06
    (distance
    0.06
    をした
    0.06
    (asset
    0.06
    archs
    0.06
     PICK
    0.06
    (offset
    0.06
    Activations Density 0.000%

    No Known Activations