© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126311
    Prev
    Next
    INDEX
    Explanations

    falling short

    np_max-act · gemini-2.0-flash

    This neuron detects words that express falling just below or missing a goal—particularly “short” or “shy” in constructions like “fell short of” or “shy of.”

    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
    existing
    -0.06
    Japanese
    -0.06
     Thế
    -0.06
    -split
    -0.06
    iences
    -0.06
    407
    -0.06
     CHANNEL
    -0.06
    チェ
    -0.06
     مقایسه
    -0.06
     Fluid
    -0.06
    POSITIVE LOGITS
    )object
    0.09
    nímu
    0.08
    ="">
↵
    0.08
     탄
    0.07
     내려
    0.07
     getImage
    0.07
    >(()
    0.07
    	iVar
    0.06
    (()
    0.06
    ıyorum
    0.06
    Activations Density 0.007%

    No Known Activations