© 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. 110586
    Prev
    Next
    INDEX
    Explanations

    debugging output

    np_max-act · gemini-2.0-flash

    The neuron activates on in‐code debugging or logging calls and macros (e.g. print, printk, DBG, DPRINTK, RPC_DBG).

    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
     religions
    -0.07
    120
    -0.07
     да
    -0.06
    าม
    -0.06
     бороть
    -0.06
     mund
    -0.06
    ueil
    -0.06
    Ком
    -0.06
    に向
    -0.06
    .ToLower
    -0.06
    POSITIVE LOGITS
     ،
    0.07
    "';
    0.07
     damaged
    0.07
     futures
    0.06
    :string
    0.06
    activo
    0.06
     tr
    0.06
    양
    0.06
     ".$_
    0.06
    	JOptionPane
    0.06
    Activations Density 0.005%

    No Known Activations