© 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. 85782
    Prev
    Next
    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash

    legal terminology and procedural language in court documents.

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

    The neuron fires on the ending “signature” lines and metadata of court orders—e.g. the “DATED:” token and the “/s/” signature slashes and adjoining tokens that mark the judge’s signature block.

    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
     öğ
    -0.06
    .texture
    -0.06
    adding
    -0.06
    国内
    -0.06
    setOnClickListener
    -0.06
    HostException
    -0.06
     hearty
    -0.06
     Marco
    -0.06
     Nikki
    -0.06
     Resort
    -0.06
    POSITIVE LOGITS
     Represent
    0.06
     swear
    0.06
    achable
    0.06
    体
    0.06
     Elekt
    0.06
     Rein
    0.06
    سر
    0.06
     sala
    0.06
    ateral
    0.06
    ambda
    0.06
    Activations Density 0.002%

    No Known Activations