Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 81067
    Prev
    Next
    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash

    specific programming terms and functions related to text rendering.

    oai_token-act-pair · gpt-4o-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
    CU
    -0.07
    Department
    -0.07
     Liter
    -0.07
    _perf
    -0.07
    pan
    -0.07
    PTR
    -0.06
     bob
    -0.06
    Bond
    -0.06
     likeness
    -0.06
    Disconnect
    -0.06
    POSITIVE LOGITS
     ایجاد
    0.08
     سال
    0.07
     popul
    0.06
     自动生成
    0.06
    .upper
    0.06
    เง
    0.06
     �
    0.06
     Greenville
    0.06
     stage
    0.06
     สาข
    0.06
    Activations Density 0.020%

    No Known Activations