© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44149
    Prev
    Next
    INDEX
    Explanations

    project teamwork manufacturing maintenance demos

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of hands-on craft or creative production activities (e.g. sewing, weaving, painting, pattern-making).

    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
    uzzy
    -0.07
     Oven
    -0.07
    _student
    -0.07
     bons
    -0.07
    .curve
    -0.07
    پر
    -0.07
     oven
    -0.07
     Cam
    -0.06
    bpp
    -0.06
    ASK
    -0.06
    POSITIVE LOGITS
     Installer
    0.06
     APA
    0.06
     ``(
    0.06
     addItem
    0.06
     mediaPlayer
    0.06
    	GLuint
    0.06
     Spam
    0.05
    �
    0.05
    ziej
    0.05
     '%$
    0.05
    Activations Density 0.149%

    No Known Activations