© 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
    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. 110425
    Prev
    Next
    INDEX
    Explanations

    systems

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on mentions of technical “system(s)” or “technology,” i.e. references to engineered or technological systems.

    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
     прич
    -0.08
    _Metadata
    -0.07
    Drawable
    -0.06
     ICMP
    -0.06
     concentration
    -0.06
    	password
    -0.06
    	override
    -0.06
     toxicity
    -0.06
    _probe
    -0.06
    _compat
    -0.06
    POSITIVE LOGITS
    ）:
    0.07
    -build
    0.06
     paran
    0.06
     cerr
    0.06
     unleashed
    0.06
     Brilliant
    0.06
    ence
    0.06
    -END
    0.06
    σματα
    0.06
    011
    0.06
    Activations Density 0.027%

    No Known Activations