© 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. 128839
    Prev
    Next
    INDEX
    Explanations

    URLs related to issues

    np_max-act · gemini-2.0-flash

    The neuron is picking out references to external resource URLs (e.g. issue-tracker or patent links).

    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
     김
    -0.07
    plotlib
    -0.07
    -inspired
    -0.06
     Apprentice
    -0.06
    COMPARE
    -0.06
    зу
    -0.06
    Program
    -0.06
     forthcoming
    -0.06
     accessed
    -0.06
    SceneManager
    -0.06
    POSITIVE LOGITS
     datingside
    0.07
     ani
    0.07
    ISTIC
    0.07
    立刻
    0.07
     حکوم
    0.06
     인
    0.06
     července
    0.06
    .beta
    0.06
     strSQL
    0.06
     carrera
    0.06
    Activations Density 0.083%

    No Known Activations