© 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. 91736
    Prev
    Next
    INDEX
    Explanations

    intimate

    np_max-act · gemini-2.0-flash

    references to intimacy and deep emotional connections in a variety of contexts.

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

    This neuron is triggered by the word “intimate” when it appears as an adjective describing a relationship, scene, or context.

    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
    (dataSource
    -0.07
    Spring
    -0.07
     cyclic
    -0.07
     Feld
    -0.07
     Spring
    -0.07
    егод
    -0.06
     fallen
    -0.06
    -wheel
    -0.06
     fail
    -0.06
    Rol
    -0.06
    POSITIVE LOGITS
     intimate
    0.13
     intimately
    0.12
     intimacy
    0.11
     intim
    0.08
    mt
    0.07
    ít
    0.07
    tě
    0.07
     Sm
    0.07
     thù
    0.06
    近
    0.06
    Activations Density 0.004%

    No Known Activations