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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 118392
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash

    phrases indicating travel itineraries and plans.

    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
    -follow
    -0.07
     EXPER
    -0.07
    externalActionCode
    -0.07
    Reservation
    -0.07
    -sur
    -0.06
     Mesa
    -0.06
    -viol
    -0.06
    -mount
    -0.06
     wander
    -0.06
    .putInt
    -0.06
    POSITIVE LOGITS
    ritt
    0.07
     потріб
    0.06
    results
    0.06
    �
    0.06
     BOARD
    0.06
    列
    0.06
     thoại
    0.06
     ngang
    0.06
     clk
    0.05
    境
    0.05
    Activations Density 0.009%

    No Known Activations