© 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. 109823
    Prev
    Next
    INDEX
    Explanations

    This neuron primarily fires on the “=” token, i.e. instances of an equals sign (assignment or equation delimiter).

    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
    95
    -0.08
    lıyor
    -0.07
    lerle
    -0.07
     IE
    -0.06
     servers
    -0.06
    obec
    -0.06
    40
    -0.06
    _MANAGER
    -0.06
     程
    -0.06
    25
    -0.06
    POSITIVE LOGITS
     년도별
    0.07
     وخ
    0.07
     động
    0.06
    	Entity
    0.06
     어떻게
    0.06
     منها
    0.06
     vow
    0.06
     StatusBar
    0.06
    UserInfo
    0.06
    icable
    0.06
    Activations Density 0.000%

    No Known Activations