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. 43830
    Prev
    Next
    INDEX
    Explanations

    chemical formulas

    np_max-act · gemini-2.0-flash

    chemical compounds and their production processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects numeric position prefixes (e.g. “4-N,” “2-I,” “6-Chloro-”) used in systematic chemical compound names.

    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
    matchCondition
    -0.07
     Tyr
    -0.07
     �
    -0.07
     keyCode
    -0.07
    _AES
    -0.07
    щин
    -0.06
    �
    -0.06
    AuthToken
    -0.06
    Around
    -0.06
    _wo
    -0.06
    POSITIVE LOGITS
     regulates
    0.07
    ]),
    0.06
     frightening
    0.06
    ıyorum
    0.06
    ifornia
    0.06
     başarılı
    0.06
    anny
    0.06
    VisualStyle
    0.06
     Changed
    0.06
     Counseling
    0.06
    Activations Density 0.021%

    No Known Activations