© 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. 42637
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find standalone Arabic numerals (tokens consisting solely of digits).

    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
    	device
    -0.07
     ngữ
    -0.06
     sanity
    -0.06
    렴
    -0.06
    pper
    -0.06
     fleece
    -0.06
     eru
    -0.06
     ers
    -0.06
     encore
    -0.06
     roaming
    -0.06
    POSITIVE LOGITS
    -existent
    0.07
     Παρ
    0.06
     peculiar
    0.06
    usting
    0.06
     mListener
    0.06
     sporting
    0.06
    άρ
    0.06
    _alignment
    0.06
    _TR
    0.06
    findAll
    0.06
    Activations Density 0.620%

    No Known Activations