© 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. 54250
    Prev
    Next
    INDEX
    Explanations

    is that

    np_max-act · gemini-2.0-flash

    The neuron detects linking or explanatory phrases—particularly instances of “that is,” “way that is,” and similar constructions used to define or describe attributes.

    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
    setChecked
    -0.07
    ść
    -0.07
     IllegalStateException
    -0.07
    的话
    -0.07
     escalate
    -0.07
    _SUPPLY
    -0.07
    (wrapper
    -0.07
     رشد
    -0.07
    feature
    -0.06
    ernaut
    -0.06
    POSITIVE LOGITS
    -rel
    0.06
    Label
    0.06
     xmin
    0.06
    Ret
    0.06
     وی
    0.06
     Contin
    0.06
     limite
    0.06
    vide
    0.05
     Cargo
    0.05
     короб
    0.05
    Activations Density 0.034%

    No Known Activations