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. 129410
    Prev
    Next
    INDEX
    Explanations

    solar

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the phrase “solar system.”

    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
    ات
    -0.07
     subclass
    -0.07
    ا�
    -0.07
    .JPG
    -0.07
     Logout
    -0.07
     ノ
    -0.07
    _advance
    -0.07
    target
    -0.06
     Jill
    -0.06
     promotes
    -0.06
    POSITIVE LOGITS
     System
    0.07
    @Json
    0.06
    ighter
    0.06
    Flex
    0.06
    alars
    0.06
    เคร
    0.06
     ruling
    0.06
     pulls
    0.06
    债
    0.06
     dém
    0.06
    Activations Density 0.004%

    No Known Activations