© 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. 55929
    Prev
    Next
    INDEX
    Explanations

    Optional

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing decimal or floating‐point values.

    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
    ?=
    -0.07
    AccessorType
    -0.07
     MacBook
    -0.06
    OU
    -0.06
     dissip
    -0.06
     ctrl
    -0.06
     saturn
    -0.06
     shifts
    -0.06
     podpor
    -0.06
     стра
    -0.06
    POSITIVE LOGITS
    أة
    0.06
    прав
    0.06
    realDonaldTrump
    0.06
     прой
    0.06
    MITTED
    0.06
     nature
    0.06
     א
    0.06
     Turing
    0.06
     Correspond
    0.06
    .getRaw
    0.06
    Activations Density 1.507%

    No Known Activations