© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109751
    Prev
    Next
    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash

    letters expressing personal sentiments and updates regarding significant life events.

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

    The neuron detects intimate, first‐person emotional expressions in personal letters (e.g. pronouns like “I” and “you” along with heartfelt phrases).

    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
    ’en
    -0.07
     například
    -0.07
    .VERSION
    -0.07
     любой
    -0.06
    >t
    -0.06
    -den
    -0.06
    иф
    -0.06
    FG
    -0.06
    Meta
    -0.06
    universal
    -0.06
    POSITIVE LOGITS
     christ
    0.07
    씨
    0.06
     getResources
    0.06
    ічні
    0.06
     німець
    0.06
     sill
    0.06
    reh
    0.06
    دری
    0.06
     Carn
    0.06
     conson
    0.06
    Activations Density 0.049%

    No Known Activations