© 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. 44674
    Prev
    Next
    INDEX
    Explanations

    executable

    np_max-act · gemini-2.0-flash

    This neuron detects instructions about making a script (or file) executable, especially via chmod or setting executable permissions.

    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
     относится
    -0.07
     До
    -0.07
     العلم
    -0.06
     imageSize
    -0.06
     boiled
    -0.06
    �
    -0.06
     besie
    -0.06
     concatenated
    -0.06
     consort
    -0.06
    	BOOST
    -0.06
    POSITIVE LOGITS
    gable
    0.07
    able
    0.07
    PTY
    0.07
    Let
    0.07
    perm
    0.06
    Create
    0.06
    Cannot
    0.06
    hee
    0.06
                
    ↵
    0.06
    ThemeProvider
    0.06
    Activations Density 0.002%

    No Known Activations