© 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. 76340
    Prev
    Next
    INDEX
    Explanations

    hola

    np_max-act · gemini-2.0-flash

    Spanish greetings or informal expressions of welcome.

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

    This neuron activates on the Spanish greeting “hola,” i.e. it detects when the user says “hola” at the start of a message.

    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
    ),"
    -0.06
    汗
    -0.06
    Prefs
    -0.06
    dur
    -0.06
    ErrorMsg
    -0.06
    bigint
    -0.06
    $app
    -0.06
    004
    -0.06
     внеш
    -0.06
    .sav
    -0.06
    POSITIVE LOGITS
    ř
    0.07
     věd
    0.07
     occurs
    0.06
    čas
    0.06
     postings
    0.06
    wa
    0.06
     ain
    0.06
     Ι
    0.06
    Observer
    0.06
     moda
    0.06
    Activations Density 0.012%

    No Known Activations