© 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. 126038
    Prev
    Next
    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on the “TH” ordinal suffix (as in “5TH CIRCUIT”), i.e. the “TH” ending of ordinal abbreviations.

    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
     Tasks
    -0.07
     iken
    -0.07
     устройства
    -0.06
    contract
    -0.06
     информации
    -0.06
     elementos
    -0.06
     Arbeit
    -0.06
    lığını
    -0.06
     sosyal
    -0.06
     equality
    -0.06
    POSITIVE LOGITS
     Carnival
    0.07
    /css
    0.06
     TODAY
    0.06
    /ts
    0.06
    ResultSet
    0.06
     tabIndex
    0.06
     Leafs
    0.06
     epile
    0.06
    _hide
    0.06
     figsize
    0.06
    Activations Density 0.001%

    No Known Activations