© 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
    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. 73605
    Prev
    Next
    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash

    medical terms related to surgical procedures and patient outcomes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron selectively activates on words that mark an initial or primary stage or event (e.g. “first,” “primary,” “initial,” “single”).

    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
    ropri
    -0.06
     百度流量
    -0.06
     dz
    -0.06
     теат
    -0.06
     heels
    -0.06
    .callbacks
    -0.06
    .Default
    -0.06
    portfolio
    -0.06
    .STATUS
    -0.06
    処
    -0.06
    POSITIVE LOGITS
                
    ↵
    0.07
    >/
    0.07
    》(
    0.07
    úp
    0.07
    beth
    0.06
    ويس
    0.06
    Pets
    0.06
    !
    0.06
                    
    ↵
    0.06
    ervo
    0.06
    Activations Density 0.015%

    No Known Activations