© 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. 73648
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron is looking for string‐slicing operations (e.g. calls to slice, substring, etc.) in code.

    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
     色
    -0.07
     Went
    -0.07
    کش
    -0.07
     Lydia
    -0.07
     Somali
    -0.06
    วาง
    -0.06
     즐
    -0.06
     Năm
    -0.06
    拍
    -0.06
     B
    -0.06
    POSITIVE LOGITS
    owan
    0.07
    ISM
    0.07
    월부터
    0.06
     separ
    0.06
    omics
    0.06
     split
    0.06
    awe
    0.06
     senators
    0.06
     replicas
    0.06
     draft
    0.05
    Activations Density 0.009%

    No Known Activations