Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 43981
    Prev
    Next
    INDEX
    Explanations

    shelf

    np_max-act · gemini-2.0-flash

    The neuron triggers on mentions of product stability and shelf-life or storage duration characteristics.

    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
    _K
    -0.07
     ska
    -0.07
     migrations
    -0.07
     mob
    -0.06
    .Initial
    -0.06
     sample
    -0.06
    Fine
    -0.06
     observing
    -0.06
     anticipation
    -0.06
    일본
    -0.06
    POSITIVE LOGITS
    	auto
    0.06
     consume
    0.06
    aligned
    0.06
     вра
    0.06
     ∀
    0.06
     石
    0.06
     overs
    0.06
    �
    0.06
     peně
    0.06
     owns
    0.06
    Activations Density 0.008%

    No Known Activations