© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7472
    Prev
    Next
    INDEX
    Explanations

    result

    np_max-act · gemini-2.0-flash

    The neuron detects concluding summary phrases—particularly occurrences of the word “result” in “The result is…”–type sentences.

    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
     Din
    -0.07
     adicion
    -0.07
     Rum
    -0.07
     Dom
    -0.06
    elt
    -0.06
     Numero
    -0.06
    issance
    -0.06
    اران
    -0.06
    　　　　　　 　
    -0.06
    ریان
    -0.06
    POSITIVE LOGITS
     result
    0.12
     resulted
    0.08
     results
    0.08
     effect
    0.07
     Results
    0.07
     outcome
    0.07
    *q
    0.06
     '<?
    0.06
    .average
    0.06
    ，将
    0.06
    Activations Density 0.023%

    No Known Activations