© 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. 125996
    Prev
    Next
    INDEX
    Explanations

    construction

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of structural building materials or components (e.g., lumber, joists, beams, posts) in construction contexts.

    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
    こん
    -0.07
     딸
    -0.07
     derby
    -0.06
    pod
    -0.06
    �
    -0.06
     idols
    -0.06
     Чем
    -0.06
     suicidal
    -0.06
    	bytes
    -0.06
    лет
    -0.06
    POSITIVE LOGITS
    ilir
    0.06
    _BR
    0.06
     saya
    0.06
    стю
    0.06
    Coal
    0.06
    responsive
    0.06
    ieved
    0.06
     Direction
    0.06
     fluorescent
    0.06
     lite
    0.06
    Activations Density 0.017%

    No Known Activations