© 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. 91125
    Prev
    Next
    INDEX
    Explanations

    irect

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “indirect” (e.g. as a section heading or label).

    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
    Kelly
    -0.07
     chore
    -0.07
    izioni
    -0.06
     cram
    -0.06
    CELER
    -0.06
     Daddy
    -0.06
     farms
    -0.06
    oun
    -0.06
    caling
    -0.06
     clans
    -0.06
    POSITIVE LOGITS
     indirect
    0.09
     Indicator
    0.08
     ou
    0.07
    �
    0.07
     indirectly
    0.07
     enclosed
    0.07
     �
    0.07
    .toDouble
    0.07
    اغ
    0.07
     remote
    0.07
    Activations Density 0.005%

    No Known Activations