© 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. 44601
    Prev
    Next
    INDEX
    Explanations

    must

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs and phrases that express a character’s required actions or objectives—especially “must,” “find,” “use,” “navigate,” and similar goal‐oriented constructions.

    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
    三三
    -0.06
    _CONV
    -0.06
    lectic
    -0.06
    ری
    -0.06
    chg
    -0.06
    初
    -0.06
    　　　 　 　 　
    -0.06
    _allocator
    -0.06
     inversion
    -0.06
     collaborations
    -0.06
    POSITIVE LOGITS
     літ
    0.07
     Mem
    0.07
    ás
    0.06
     leaf
    0.06
     polož
    0.06
    ını
    0.06
     einf
    0.06
    SC
    0.06
    ście
    0.06
     inserted
    0.06
    Activations Density 0.027%

    No Known Activations