© 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. 92425
    Prev
    Next
    INDEX
    Explanations

    /local

    np_max-act · gemini-2.0-flash

    This neuron detects filesystem path segments, particularly references to absolute install directories like `/usr/local` and its subpaths.

    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
    manız
    -0.06
     humiliating
    -0.06
     Chaos
    -0.06
    _Thread
    -0.06
     liquor
    -0.06
    ([...
    -0.06
     ids
    -0.06
     혼
    -0.06
     enemies
    -0.06
    arehouse
    -0.06
    POSITIVE LOGITS
    /local
    0.09
    RAL
    0.08
    	REG
    0.07
     overclock
    0.07
     spa
    0.07
     microwave
    0.07
     UV
    0.07
     soci
    0.07
    A
    0.07
     �
    0.07
    Activations Density 0.001%

    No Known Activations