© 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. 89849
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    This neuron detects verbs related to granting priority access or use of resources or facilities (e.g., “have priority use,” “access,” “prepare”).

    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
     phân
    -0.07
    town
    -0.07
    ंट
    -0.06
     olmak
    -0.06
     Cone
    -0.06
    _of
    -0.06
    nock
    -0.06
     ～
    -0.06
    anie
    -0.06
     Bolshevik
    -0.06
    POSITIVE LOGITS
    糖
    0.07
    .SetKeyName
    0.07
    decorators
    0.07
     získ
    0.07
    [slot
    0.07
    Mixin
    0.07
    	assertNotNull
    0.07
    _patient
    0.06
    .fullName
    0.06
    .formData
    0.06
    Activations Density 0.149%

    No Known Activations