© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89009
    Prev
    Next
    INDEX
    Explanations

    quantum computing

    np_max-act · gemini-2.0-flash

    The neuron flags tokens in the model’s generated (assistant) text, activating on nearly every word in assistant replies and remaining off in user input.

    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
    .Dec
    -0.07
    Deg
    -0.06
     estr
    -0.06
     machines
    -0.06
     relate
    -0.06
    maker
    -0.06
    過
    -0.06
    _song
    -0.06
    ̧
    -0.06
     indication
    -0.06
    POSITIVE LOGITS
    Variables
    0.06
    CLICK
    0.06
    	Send
    0.06
     způsob
    0.06
    Tiles
    0.06
    PY
    0.06
    $('.
    0.06
     أد
    0.06
    ~-~-
    0.06
     Joey
    0.06
    Activations Density 0.020%

    No Known Activations