Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125887
    Prev
    Next
    INDEX
    Explanations

    granted

    np_max-act · gemini-2.0-flash

    The neuron detects the formal announcement that a court has granted a petition for review or leave to appeal.

    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
     winds
    -0.08
    logic
    -0.07
    FORM
    -0.07
    اهم
    -0.07
     optim
    -0.07
     Hide
    -0.06
     hybrids
    -0.06
    indows
    -0.06
     hours
    -0.06
    eld
    -0.06
    POSITIVE LOGITS
    tainment
    0.07
    .FileInputStream
    0.06
    dataProvider
    0.06
    _SECURITY
    0.06
    (datos
    0.06
    (MediaType
    0.06
    propertyName
    0.06
    TagName
    0.06
    \Data
    0.06
     confiscated
    0.06
    Activations Density 0.006%

    No Known Activations