© 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. 89015
    Prev
    Next
    INDEX
    Explanations

    ocean

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “ocean” (and closely related forms).

    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
     laat
    -0.08
     BU
    -0.07
    .grade
    -0.07
    PCODE
    -0.07
    戴
    -0.06
    иру
    -0.06
    .Hide
    -0.06
     ї
    -0.06
     permit
    -0.06
    .da
    -0.06
    POSITIVE LOGITS
     Ocean
    0.16
     ocean
    0.14
    Ocean
    0.11
     oceans
    0.10
    cean
    0.08
     øns
    0.07
     telecommunications
    0.07
     통
    0.07
    洋
    0.07
     land
    0.07
    Activations Density 0.005%

    No Known Activations