© 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
    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. 55780
    Prev
    Next
    INDEX
    Explanations

    trip

    np_max-act · gemini-2.0-flash

    references to travel experiences and activities.

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

    The neuron consistently activates on the word “trip,” indicating it detects mentions of “trip” in travel or itinerary contexts.

    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
     Μέ
    -0.07
    产业
    -0.06
    ALE
    -0.06
    élé
    -0.06
    еле
    -0.06
     safeguard
    -0.06
     le
    -0.06
    Le
    -0.06
    olet
    -0.06
    ale
    -0.06
    POSITIVE LOGITS
     trip
    0.19
     Trip
    0.14
     trips
    0.13
    Trip
    0.11
    trip
    0.10
    .trip
    0.08
     TimeZone
    0.08
    _trip
    0.08
     expedition
    0.07
    ropping
    0.07
    Activations Density 0.009%

    No Known Activations