© 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. 8810
    Prev
    Next
    INDEX
    Explanations

    ships and docks

    np_max-act · gemini-2.0-flash

    historical context and significance related to maritime events or figures.

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

    The neuron activates on words and phrases referring to a ship being docked, moored, anchored, or berthed.

    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
    ynthesis
    -0.07
    032
    -0.06
    nim
    -0.06
    oca
    -0.06
     Bus
    -0.06
     SDLK
    -0.06
    當
    -0.06
    xs
    -0.06
    silent
    -0.06
    erca
    -0.06
    POSITIVE LOGITS
    **↵
    0.07
    ↵
    0.07
    :Boolean
    0.07
    TextField
    0.06
     imagining
    0.06
     handleSubmit
    0.06
     NSStringFromClass
    0.06
    (Texture
    0.06
     teaches
    0.06
     induces
    0.06
    Activations Density 0.029%

    No Known Activations