© 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. 6409
    Prev
    Next
    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash

    The neuron specifically spots bits of legal citation strings—tokens that occur in case‐reporter references (e.g. “C t. App.” and similar court/volume abbreviations).

    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
     FAST
    -0.07
    .shuffle
    -0.06
     Merkezi
    -0.06
    eným
    -0.06
    parity
    -0.06
     abruptly
    -0.06
    FAST
    -0.06
     nær
    -0.06
     成
    -0.06
     Watts
    -0.06
    POSITIVE LOGITS
     Rewrite
    0.07
    -native
    0.07
    dish
    0.07
     reverse
    0.06
    :true
    0.06
     Metals
    0.06
    ُون
    0.06
     infiltr
    0.06
     Assertions
    0.06
    =N
    0.06
    Activations Density 0.005%

    No Known Activations