© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73824
    Prev
    Next
    INDEX
    Explanations

    legal/official filings

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric values—digits, numbers, percentages, and similar statistical tokens.

    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
     monstrous
    -0.06
    όν
    -0.06
    )n
    -0.06
     Nights
    -0.06
     });↵↵↵↵
    -0.06
    _stdout
    -0.05
     Reich
    -0.05
    sert
    -0.05
     Fuj
    -0.05
     secs
    -0.05
    POSITIVE LOGITS
    landscape
    0.07
    \core
    0.07
    [jj
    0.07
    (filters
    0.07
    AdapterManager
    0.07
     Fat
    0.07
    _MISC
    0.07
    	Connection
    0.07
    (inode
    0.07
    _____
    0.07
    Activations Density 0.022%

    No Known Activations