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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 126479
    Prev
    Next
    INDEX
    Explanations

    Stars and parallax measurements

    np_max-act · gemini-2.0-flash

    The neuron activates on terms and subword pieces related to stellar parallax and astrometric distance measurements.

    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
     автор
    -0.07
    Japan
    -0.07
     nearly
    -0.06
    mul
    -0.06
     })}↵
    -0.06
    ']}'
    -0.06
     spend
    -0.06
     Nora
    -0.06
     मज
    -0.06
     rewritten
    -0.06
    POSITIVE LOGITS
    359
    0.08
     XS
    0.07
    allax
    0.07
    UIScreen
    0.07
     Specify
    0.06
    _BUS
    0.06
    342
    0.06
    ��
    0.06
     lastname
    0.06
     Pick
    0.06
    Activations Density 0.001%

    No Known Activations