© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29896
    Prev
    Next
    INDEX
    Explanations

    time computation in legal contexts

    np_max-act · gemini-2.0-flash

    This neuron detects language marking the start or running of a time period or deadline (e.g., verbs like “began,” “running,” “starts,” and associated numeric dates or durations).

    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
    gv
    -0.06
     cooled
    -0.06
     chairs
    -0.06
     merges
    -0.05
    generation
    -0.05
    ิท
    -0.05
     strips
    -0.05
     terminated
    -0.05
     سری
    -0.05
     filtering
    -0.05
    POSITIVE LOGITS
     j
    0.07
    .getApp
    0.07
    _Instance
    0.07
    (close
    0.07
    IDDLE
    0.07
    _secret
    0.07
    ;y
    0.07
    .wr
    0.07
    (rd
    0.07
     de
    0.06
    Activations Density 0.008%

    No Known Activations