© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54237
    Prev
    Next
    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    The neuron selectively lights up on sequences of digits—e.g. volume numbers, years, page ranges—i.e. numeric tokens in citations or dates.

    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
     Samar
    -0.07
     tennis
    -0.07
    -head
    -0.07
    913
    -0.07
    _LCD
    -0.07
    hare
    -0.06
    699
    -0.06
    _SIZE
    -0.06
    Tick
    -0.06
     valu
    -0.06
    POSITIVE LOGITS
     sns
    0.07
    -Headers
    0.07
     م
    0.06
     #{@
    0.06
    .IsTrue
    0.06
     simultaneously
    0.06
    dbo
    0.06
    AUTO
    0.06
     ResponseEntity
    0.06
     пог
    0.06
    Activations Density 0.004%

    No Known Activations