© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12708
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash

    This neuron detects the numeric position indicators used in bracketed chemical ring descriptors (e.g. the “3,2-d” in thieno[3,2-d]pyridine).

    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
    ToOne
    -0.07
     þ
    -0.06
     OPTIONAL
    -0.06
     phoenix
    -0.06
     GPU
    -0.06
    validated
    -0.06
     oo
    -0.06
    _subject
    -0.06
     história
    -0.06
     whisky
    -0.06
    POSITIVE LOGITS
    <View
    0.07
    _guess
    0.07
    ynchron
    0.06
     violates
    0.06
     vài
    0.06
    stu
    0.06
     alıp
    0.06
    cbd
    0.06
    \ActiveForm
    0.06
     Transit
    0.06
    Activations Density 0.005%

    No Known Activations