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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 73133
    Prev
    Next
    INDEX
    Explanations

    measurements and quantities

    np_max-act · gemini-2.0-flash

    references to events or actions related to health and safety.

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

    The neuron flags numeric time‐and‐duration expressions—especially hours, minutes, and similar measurements.

    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
     ocur
    -0.07
    isers
    -0.06
     tong
    -0.06
    <Category
    -0.06
    HV
    -0.06
    ùi
    -0.06
    ynth
    -0.06
     DN
    -0.06
    arc
    -0.06
     erreur
    -0.06
    POSITIVE LOGITS
     �
    0.06
     componentWillMount
    0.06
     filme
    0.06
    단
    0.06
     Miche
    0.06
     userAgent
    0.06
     marches
    0.06
     здоб
    0.06
     mainScreen
    0.06
     Storm
    0.06
    Activations Density 0.078%

    No Known Activations